BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//CMSA - ECPv6.15.20//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-ORIGINAL-URL:https://cmsa.fas.harvard.edu
X-WR-CALDESC:Events for CMSA
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-Robots-Tag:noindex
X-PUBLISHED-TTL:PT1H
BEGIN:VTIMEZONE
TZID:America/New_York
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20210314T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20211107T060000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20220313T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20221106T060000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20230312T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20231105T060000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20240310T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20241103T060000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20231025T140000
DTEND;TZID=America/New_York:20231025T150000
DTSTAMP:20260515T141950
CREATED:20240223T105453Z
LAST-MODIFIED:20240223T105453Z
UID:10002853-1698242400-1698246000@cmsa.fas.harvard.edu
SUMMARY:Llemma: an open language model for mathematics
DESCRIPTION:New Technologies in Mathematics Seminar \nSpeaker: Sean Welleck\, CMU\, Language Technologies Institute \nTitle: Llemma: an open language model for mathematics \nAbstract: We present Llemma: 7 billion and 34 billion parameter language models for mathematics. The Llemma models are initialized with Code Llama weights\, then trained on the Proof-Pile II\, a 55 billion token dataset of mathematical web data\, code\, and scientific papers. The resulting models show improved mathematical capabilities\, and can be adapted to various tasks. For instance\, Llemma outperforms the unreleased Minerva model suite on an equi-parameter basis\, and is capable of tool use and formal theorem proving without any further fine-tuning. We openly release all artifacts\, including the Llemma models\, the Proof-Pile II\, and code to replicate our experiments. We hope that Llemma serves as a platform for new research and tools at the intersection of generative models and mathematics. \n  \n 
URL:https://cmsa.fas.harvard.edu/event/nt-102523/
LOCATION:CMSA Room G10\, CMSA\, 20 Garden Street\, Cambridge\, MA\, 02138\, United States
CATEGORIES:New Technologies in Mathematics Seminar
ATTACH;FMTTYPE=image/png:https://cmsa.fas.harvard.edu/media/NTM-10.25.2023.png
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20231018T140000
DTEND;TZID=America/New_York:20231018T150000
DTSTAMP:20260515T141950
CREATED:20240223T114049Z
LAST-MODIFIED:20240223T114049Z
UID:10002867-1697637600-1697641200@cmsa.fas.harvard.edu
SUMMARY:Physics of Language Models: Knowledge Storage\, Extraction\, and Manipulation
DESCRIPTION:New Technologies in Mathematics Seminar \nSpeaker: Yuanzhi Li\, CMU Dept. of Machine Learning and Microsoft Research \nTitle: Physics of Language Models: Knowledge Storage\, Extraction\, and Manipulation \nAbstract: Large language models (LLMs) can memorize a massive amount of knowledge during pre-training\, but can they effectively use this knowledge at inference time? In this work\, we show several striking results about this question. Using a synthetic biography dataset\, we first show that even if an LLM achieves zero training loss when pretraining on the biography dataset\, it sometimes can not be finetuned to answer questions as simple as “What is the birthday of XXX” at all. We show that sufficient data augmentation during pre-training\, such as rewriting the same biography multiple times or simply using the person’s full name in every sentence\, can mitigate this issue. Using linear probing\, we unravel that such augmentation forces the model to store knowledge about a person in the token embeddings of their name rather than other locations. \nWe then show that LLMs are very bad at manipulating knowledge they learn during pre-training unless a chain of thought is used at inference time. We pretrained an LLM on the synthetic biography dataset\, so that it could answer “What is the birthday of XXX” with 100% accuracy.  Even so\, it could not be further fine-tuned to answer questions like “Is the birthday of XXX even or odd?” directly.  Even using Chain of Thought training data only helps the model answer such questions in a CoT manner\, not directly. \nWe will also discuss preliminary progress on understanding the scaling law of how large a language model needs to be to store X pieces of knowledge and extract them efficiently. For example\, is a 1B parameter language model enough to store all the knowledge of a middle school student? \n  \n 
URL:https://cmsa.fas.harvard.edu/event/nt-101823/
LOCATION:CMSA Room G10\, CMSA\, 20 Garden Street\, Cambridge\, MA\, 02138\, United States
CATEGORIES:New Technologies in Mathematics Seminar
ATTACH;FMTTYPE=image/png:https://cmsa.fas.harvard.edu/media/NTM-10.18.2023.png
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20231011T140000
DTEND;TZID=America/New_York:20231011T150000
DTSTAMP:20260515T141950
CREATED:20240223T114336Z
LAST-MODIFIED:20240223T114336Z
UID:10002868-1697032800-1697036400@cmsa.fas.harvard.edu
SUMMARY:LeanDojo: Theorem Proving with Retrieval-Augmented Language Models
DESCRIPTION:New Technologies in Mathematics Seminar \nSpeaker: Alex Gu\, MIT Dept. of EE&CS \nTitle: LeanDojo: Theorem Proving with Retrieval-Augmented Language Models \nAbstract: Large language models (LLMs) have shown promise in proving formal theorems using proof assistants such as Lean. However\, existing methods are difficult to reproduce or build on\, due to private code\, data\, and large compute requirements. This has created substantial barriers to research on machine learning methods for theorem proving. We introduce LeanDojo: an open-source Lean playground consisting of toolkits\, data\, models\, and benchmarks. LeanDojo extracts data from Lean and enables interaction with the proof environment programmatically. It contains fine-grained annotations of premises in proofs\, providing valuable data for premise selection: a key bottleneck in theorem proving. Using this data\, we develop ReProver (Retrieval-Augmented Prover): the first LLM-based prover that is augmented with retrieval for selecting premises from a vast math library. It is inexpensive and needs only one GPU week of training. Our retriever leverages LeanDojo’s program analysis capability to identify accessible premises and hard negative examples\, which makes retrieval much more effective. Furthermore\, we construct a new benchmark consisting of 96\,962 theorems and proofs extracted from Lean’s math library. It features a challenging data split requiring the prover to generalize to theorems relying on novel premises that are never used in training. We use this benchmark for training and evaluation\, and experimental results demonstrate the effectiveness of ReProver over non-retrieval baselines and GPT-4. We thus provide the first set of open-source LLM-based theorem provers without any proprietary datasets and release it under a permissive MIT license to facilitate further research. \n 
URL:https://cmsa.fas.harvard.edu/event/nt-101123-2/
LOCATION:CMSA Room G10\, CMSA\, 20 Garden Street\, Cambridge\, MA\, 02138\, United States
CATEGORIES:New Technologies in Mathematics Seminar
ATTACH;FMTTYPE=image/png:https://cmsa.fas.harvard.edu/media/CMSA-NTM-Seminar-10.11.2023.png
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20230927T140000
DTEND;TZID=America/New_York:20230927T150000
DTSTAMP:20260515T141950
CREATED:20240227T082824Z
LAST-MODIFIED:20240227T082824Z
UID:10002872-1695823200-1695826800@cmsa.fas.harvard.edu
SUMMARY:Transformers for maths\, and maths for transformers
DESCRIPTION:New Technologies in Mathematics Seminar \nSpeaker: François Charton\, Meta AI \nTitle:  Transformers for maths\, and maths for transformers \nAbstract: Transformers can be trained to solve problems of mathematics. I present two recent applications\, in mathematics and physics: predicting integer sequences\, and discovering the properties of scattering amplitudes in a close relative of Quantum ChromoDynamics. \nProblems of mathematics can also help understand transformers. Using two examples from linear algebra and integer arithmetic\, I show that model predictions can be explained\, that trained models do not confabulate\, and that carefully choosing the training distributions can help achieve better\, and more robust\, performance. \n  \n  \n 
URL:https://cmsa.fas.harvard.edu/event/nt-92723/
LOCATION:CMSA Room G10\, CMSA\, 20 Garden Street\, Cambridge\, MA\, 02138\, United States
CATEGORIES:New Technologies in Mathematics Seminar
ATTACH;FMTTYPE=image/png:https://cmsa.fas.harvard.edu/media/CMSA-NTM-Seminar-09.27.2023.png
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20230920T140000
DTEND;TZID=America/New_York:20230920T150000
DTSTAMP:20260515T141950
CREATED:20240227T083355Z
LAST-MODIFIED:20240227T083355Z
UID:10002873-1695218400-1695222000@cmsa.fas.harvard.edu
SUMMARY:The TinyStories Dataset: How Small Can Language Models Be And Still Speak Coherent
DESCRIPTION:New Technologies in Mathematics Seminar \nSpeaker: Ronen Eldan\, Microsoft Research \nTitle: The TinyStories Dataset: How Small Can Language Models Be And Still Speak Coherent \nAbstract: While generative language models exhibit powerful capabilities at large scale\, when either the model or the number of training steps is too small\, they struggle to produce coherent and fluent text: Existing models whose size is below a few billion parameters often do not generate coherent text beyond a few sentences. Hypothesizing that one of the main reasons for the strong reliance on size is the vast breadth and abundance of patterns in the datasets used to train those models\, this motivates the following question: Can we design a dataset that preserves the essential elements of natural language\, such as grammar\, vocabulary\, facts\, and reasoning\, but that is much smaller and more refined in terms of its breadth and diversity? \nIn this talk\, we introduce TinyStories\, a synthetic dataset of short stories that only contain words that 3 to 4-year-olds typically understand\, generated by GPT-3.5/4. We show that TinyStories can be used to train and analyze language models that are much smaller than the state-of-the-art models (below 10 million parameters)\, or have much simpler architectures (with only one transformer block)\, yet still produce fluent and consistent stories with several paragraphs that are diverse and have almost perfect grammar\, and demonstrate certain reasoning capabilities. We also show that the trained models are substantially more interpretable than larger ones\, as we can visualize and analyze the attention and activation patterns of the models\, and show how they relate to the generation process and the story content. We hope that TinyStories can facilitate the development\, analysis and research of language models\, especially for low-resource or specialized domains\, and shed light on the emergence of language capabilities in LMs. \n 
URL:https://cmsa.fas.harvard.edu/event/nt-92023/
LOCATION:Virtual
CATEGORIES:New Technologies in Mathematics Seminar
ATTACH;FMTTYPE=image/png:https://cmsa.fas.harvard.edu/media/CMSA-NTM-Seminar-09.20.2023.png
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20230510T140000
DTEND;TZID=America/New_York:20230510T150000
DTSTAMP:20260515T141950
CREATED:20230809T105349Z
LAST-MODIFIED:20240228T104953Z
UID:10001225-1683727200-1683730800@cmsa.fas.harvard.edu
SUMMARY:Modern Hopfield Networks for Novel Transformer Architectures
DESCRIPTION:New Technologies in Mathematics Seminar \nSpeaker: Dmitry Krotov\, IBM Research – Cambridge \nTitle: Modern Hopfield Networks for Novel Transformer Architectures \nAbstract: Modern Hopfield Networks or Dense Associative Memories are recurrent neural networks with fixed point attractor states that are described by an energy function. In contrast to conventional Hopfield Networks\, which were popular in the 1980s\, their modern versions have a very large memory storage capacity\, which makes them appealing tools for many problems in machine learning and cognitive and neurosciences. In this talk\, I will introduce an intuition and a mathematical formulation of this class of models and will give examples of problems in AI that can be tackled using these new ideas. Particularly\, I will introduce an architecture called Energy Transformer\, which replaces the conventional attention mechanism with a recurrent Dense Associative Memory model. I will explain the theoretical principles behind this architectural choice and show promising empirical results on challenging computer vision and graph network tasks.
URL:https://cmsa.fas.harvard.edu/event/nt-51023/
LOCATION:Virtual
CATEGORIES:New Technologies in Mathematics Seminar
ATTACH;FMTTYPE=image/png:https://cmsa.fas.harvard.edu/media/CMSA-NTM-Seminar-05.10.23.png
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20230426T140000
DTEND;TZID=America/New_York:20230426T150000
DTSTAMP:20260515T141950
CREATED:20230809T103350Z
LAST-MODIFIED:20240209T151145Z
UID:10001224-1682517600-1682521200@cmsa.fas.harvard.edu
SUMMARY:Toolformer: Language Models Can Teach Themselves to Use Tools
DESCRIPTION:New Technologies in Mathematics Seminar \nSpeaker: Timo Schick\, Meta AI \nTitle: Toolformer: Language Models Can Teach Themselves to Use Tools \nAbstract: Language models exhibit remarkable abilities to solve new tasks from just a few examples or textual instructions\, especially at scale. They also\, paradoxically\, struggle with basic functionality\, such as arithmetic or factual lookup\, where much simpler and smaller models excel. In this talk\, we show how these limitations can be overcome by letting language models teach themselves to use external tools via simple APIs. We discuss Toolformer\, a model trained to independently decide which APIs to call\, when to call them\, what arguments to pass\, and how to best incorporate the results into future token prediction. Through this\, it achieves substantially improved zero-shot performance across a variety of downstream tasks without sacrificing its core language modeling abilities. \n 
URL:https://cmsa.fas.harvard.edu/event/nt-42623/
LOCATION:Virtual
CATEGORIES:New Technologies in Mathematics Seminar
ATTACH;FMTTYPE=image/png:https://cmsa.fas.harvard.edu/media/CMSA-NTM-Seminar-04.26.23.png
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20230308T140000
DTEND;TZID=America/New_York:20230308T150000
DTSTAMP:20260515T141950
CREATED:20230808T190051Z
LAST-MODIFIED:20240223T154858Z
UID:10001812-1678284000-1678287600@cmsa.fas.harvard.edu
SUMMARY:How to steer foundation models?
DESCRIPTION:New Technologies in Mathematics Seminar \nSpeaker: Jimmy Ba\, University of Toronto \nTitle: How to steer foundation models? \nAbstract: By conditioning on natural language instructions\, foundation models and large language models (LLMs) have displayed impressive capabilities as general-purpose computers. However\, task performance depends significantly on the quality of the prompt used to steer the model. Due to the lack of knowledge of how foundation models work\, most effective prompts have been handcrafted by humans through a demanding trial-and-error process. To reduce the human effort in this alignment process\, I will discuss a few approaches to steer these powerful models to excel in various downstream language and image tasks. \n 
URL:https://cmsa.fas.harvard.edu/event/nt-3823/
LOCATION:CMSA Room G10\, CMSA\, 20 Garden Street\, Cambridge\, MA\, 02138\, United States
CATEGORIES:New Technologies in Mathematics Seminar
ATTACH;FMTTYPE=image/png:https://cmsa.fas.harvard.edu/media/03.08.2023.png
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20230209T153000
DTEND;TZID=America/New_York:20230209T170000
DTSTAMP:20260515T141950
CREATED:20230705T052251Z
LAST-MODIFIED:20250328T200154Z
UID:10000063-1675956600-1675962000@cmsa.fas.harvard.edu
SUMMARY:Special Lectures on Machine Learning and Protein Folding
DESCRIPTION:The CMSA hosted a series of three 90-minute lectures on the subject of machine learning for protein folding. \nThursday Feb. 9\, Thursday Feb. 16\, & Thursday March 9\, 2023\, 3:30-5:00 pm ET \nLocation: G10\, CMSA\, 20 Garden Street\, Cambridge MA 02138 & via Zoom \n  \n  \n \nSpeaker: Nazim Bouatta\, Harvard Medical School \nAbstract: AlphaFold2\, a neural network-based model which predicts protein structures from amino acid sequences\, is revolutionizing the field of structural biology. This lecture series\, given by a leader of the OpenFold project which created an open-source version of AlphaFold2\, will explain the protein structure problem and the detailed workings of these models\, along with many new results and directions for future research. \nThursday\, Feb. 9\, 2023 \n\n\n\nThursday\, Feb. 9\, 2023 \n3:30–5:00 pm ET\nLecture 1: Machine learning for protein structure prediction\, Part 1: Algorithm space \nA brief intro to protein biology. AlphaFold2 impacts on experimental structural biology. Co-evolutionary approaches. Space of ‘algorithms’ for protein structure prediction. Proteins as images (CNNs for protein structure prediction). End-to-end differentiable approaches. Attention and long-range dependencies. AlphaFold2 in a nutshell. \n  \n \n\n\n\n  \n\n\n\nThursday\, Feb. 16\, 2023 \n3:30–5:00 pm ET\nLecture 2: Machine learning for protein structure prediction\, Part 2: AlphaFold2 architecture \nTurning the co-evolutionary principle into an algorithm: EvoFormer. Structure module and symmetry principles (equivariance and invariance). OpenFold: retraining AlphaFold2 and insights into its learning mechanisms and capacity for generalization. Applications of variants of AlphaFold2 beyond protein structure prediction: AlphaFold Multimer for protein complexes\, RNA structure prediction.\n\n\n\n  \n\n\n\nThursday\, March 9\, 2023 \n3:30–5:00 pm ET\nLecture 3: Machine learning for protein structure prediction\, Part 3: AlphaFold2 limitations and insights learned from OpenFold \nLimitations of AlphaFold2 and evolutionary ML pipelines. OpenFold: retraining AlphaFold2 yields new insights into its capacity for generalization.\n\n\n\n\n  \nBiography: Nazim Bouatta received his doctoral training in high-energy theoretical physics\, and transitioned to systems biology at Harvard Medical School\, where he received training in cellular and molecular biology in the group of Prof. Judy Lieberman. He is currently a Senior Research Fellow in the Laboratory of Systems Pharmacology led by Prof. Peter Sorger at Harvard Medical School\, and an affiliate of the Department of Systems Biology at Columbia\, in the group of Prof. Mohammed AlQuraishi. He is interested in applying machine learning\, physics\, and mathematics to biology at multiple scales. He recently co-supervised the OpenFold project\, an optimized\, trainable\, and completely open-source version of AlphaFold2. OpenFold has paved the way for many breakthroughs in biology\, including the release of the ESM Metagenomic Atlas containing over 600 million predicted protein structures. \n  \nChair: Michael Douglas (Harvard CMSA) \nModerators: Farzan Vafa & Sergiy Verstyuk (Harvard CMSA) \n\nLecture 1: Machine learning for protein structure prediction\, Part 1: Algorithm space\n \n  \nLecture 2: Machine learning for protein structure prediction\, Part 2: AlphaFold2 architecture\n \n  \nLecture 3: Machine learning for protein structure prediction\, Part 3: AlphaFold2 limitations and insights learned from OpenFold\n \n 
URL:https://cmsa.fas.harvard.edu/event/protein-folding/
LOCATION:CMSA Room G10\, CMSA\, 20 Garden Street\, Cambridge\, MA\, 02138\, United States
CATEGORIES:Event,Special Lectures,Workshop
ATTACH;FMTTYPE=image/jpeg:https://cmsa.fas.harvard.edu/media/Protein-Folding_8.5x11-scaled.jpg
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20221207T140000
DTEND;TZID=America/New_York:20221207T150000
DTSTAMP:20260515T141950
CREATED:20230808T185642Z
LAST-MODIFIED:20240116T060930Z
UID:10001215-1670421600-1670425200@cmsa.fas.harvard.edu
SUMMARY:How do Transformers reason? First principles via automata\, semigroups\, and circuits
DESCRIPTION:New Technologies in Mathematics Seminar \nSpeaker: Cyril Zhang\, Microsoft Research \nTitle: How do Transformers reason? First principles via automata\, semigroups\, and circuits \nAbstract: The current “Transformer era” of deep learning is marked by the emergence of combinatorial and algorithmic reasoning capabilities in large sequence models\, leading to dramatic advances in natural language understanding\, program synthesis\, and theorem proving. What is the nature of these models’ internal representations (i.e. how do they represent the states and computational steps of the algorithms they execute)? How can we understand and mitigate their weaknesses\, given that they resist interpretation? In this work\, we present some insights (and many further mysteries) through the lens of automata and their algebraic structure. \nSpecifically\, we investigate the apparent mismatch between recurrent models of computation (automata & Turing machines) and Transformers (which are typically shallow and non-recurrent). Using tools from circuit complexity and semigroup theory\, we characterize shortcut solutions\, whereby a shallow Transformer with only o(T) layers can exactly replicate T computational steps of an automaton. We show that Transformers can efficiently represent these shortcuts in theory; furthermore\, in synthetic experiments\, standard training successfully finds these shortcuts. We demonstrate that shortcuts can lead to statistical brittleness\, and discuss mitigations. \nJoint work with Bingbin Liu\, Jordan Ash\, Surbhi Goel\, and Akshay Krishnamurthy.
URL:https://cmsa.fas.harvard.edu/event/nt-12722/
LOCATION:CMSA Room G10\, CMSA\, 20 Garden Street\, Cambridge\, MA\, 02138\, United States
CATEGORIES:New Technologies in Mathematics Seminar
ATTACH;FMTTYPE=image/png:https://cmsa.fas.harvard.edu/media/12.07.2022.png
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20221026T140000
DTEND;TZID=America/New_York:20221026T150000
DTSTAMP:20260515T141950
CREATED:20230808T185319Z
LAST-MODIFIED:20240115T103149Z
UID:10001214-1666792800-1666796400@cmsa.fas.harvard.edu
SUMMARY:From Engine to Auto
DESCRIPTION:New Technologies in Mathematics Seminar \nSpeakers: João Araújo\, Mathematics Department\, Universidade Nova de Lisboa and Michael Kinyon\, Department of Mathematics\, University of Denver \n\nTitle: From Engine to Auto \n\n\nAbstract: Bill McCune produced the program EQP that deals with first order logic formulas and in 1996 managed to solve Robbins’ Conjecture. This very powerful tool reduces to triviality any result that can be obtained by encoding the assumptions and the goals. The next step was to turn the program into a genuine assistant for the working mathematician: find ways to help the prover with proofs; reduce the lengths of the automatic proofs to better crack them;  solve problems in higher order logic; devise tools that autonomously prove results of a given type\, etc.\n\nIn this talk we are going to show some of the tools and strategies we have been producing. There will be real illustrations of theorems obtained for groups\, loops\, semigroups\, logic algebras\, lattices and generalizations\, quandles\, and many more.
URL:https://cmsa.fas.harvard.edu/event/nt-102622/
LOCATION:CMSA Room G10\, CMSA\, 20 Garden Street\, Cambridge\, MA\, 02138\, United States
CATEGORIES:New Technologies in Mathematics Seminar
ATTACH;FMTTYPE=image/png:https://cmsa.fas.harvard.edu/media/CMSA-NTM-Seminar-10.26.2022.png
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20221019T140000
DTEND;TZID=America/New_York:20221019T150000
DTSTAMP:20260515T141950
CREATED:20230808T184955Z
LAST-MODIFIED:20240215T095357Z
UID:10001213-1666188000-1666191600@cmsa.fas.harvard.edu
SUMMARY:Towards Faithful Reasoning Using Language Models
DESCRIPTION:New Technologies in Mathematics Seminar \nSpeaker: Antonia Creswell\, DeepMind \nTitle: Towards Faithful Reasoning Using Language Models \nAbstract: Language models are showing impressive performance on many natural language tasks\, including question-answering. However\, language models – like most deep learning models – are black boxes. We cannot be sure how they obtain their answers. Do they reason over relevant knowledge to construct an answer or do they rely on prior knowledge – baked into their weights – which may be biased? An alternative approach is to develop models whose output is a human interpretable\, faithful reasoning trace leading to an answer. In this talk we will characterise faithful reasoning in terms of logically valid reasoning and demonstrate where current reasoning models fall short. Following this\, we will introduce Selection-Inference\, a faithful reasoning model\, whose causal structure mirrors the requirements for valid reasoning. We will show that our model not only produces more accurate reasoning traces but also improves final answer accuracy. \n  \n 
URL:https://cmsa.fas.harvard.edu/event/nt-101922/
LOCATION:CMSA Room G10\, CMSA\, 20 Garden Street\, Cambridge\, MA\, 02138\, United States
CATEGORIES:New Technologies in Mathematics Seminar
ATTACH;FMTTYPE=image/png:https://cmsa.fas.harvard.edu/media/10.19.2022.png
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20221005T140000
DTEND;TZID=America/New_York:20221005T160000
DTSTAMP:20260515T141950
CREATED:20230808T184616Z
LAST-MODIFIED:20240214T110102Z
UID:10001212-1664978400-1664985600@cmsa.fas.harvard.edu
SUMMARY:Minerva: Solving Quantitative Reasoning Problems with Language Models
DESCRIPTION:New Technologies in Mathematics Seminar \nSpeaker: Guy Gur-Ari\, Google Research \nTitle: Minerva: Solving Quantitative Reasoning Problems with Language Models \nAbstract: Quantitative reasoning tasks which can involve mathematics\, science\, and programming are often challenging for machine learning models in general and for language models in particular. We show that transformer-based language models obtain significantly better performance on math and science questions when trained in an unsupervised way on a large\, math-focused dataset. Performance can be further improved using prompting and sampling techniques including chain-of-thought and majority voting. Minerva\, a model that combines these techniques\, achieves SOTA on several math and science benchmarks. I will describe the model\, its capabilities and limitations.
URL:https://cmsa.fas.harvard.edu/event/minerva-solving-quantitative-reasoning-problems-with-language-models/
LOCATION:CMSA Room G10\, CMSA\, 20 Garden Street\, Cambridge\, MA\, 02138\, United States
CATEGORIES:New Technologies in Mathematics Seminar
ATTACH;FMTTYPE=image/png:https://cmsa.fas.harvard.edu/media/10.05.2022.png
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20220914T140000
DTEND;TZID=America/New_York:20220914T150000
DTSTAMP:20260515T141950
CREATED:20230808T183823Z
LAST-MODIFIED:20240301T091205Z
UID:10001210-1663164000-1663167600@cmsa.fas.harvard.edu
SUMMARY:Breaking the one-mind-barrier in mathematics using formal verification
DESCRIPTION:New Technologies in Mathematics Seminar \nSpeaker: Johan Commelin\, Mathematisches Institut\, Albert-Ludwigs-Universität Freiburg \nTitle: Breaking the one-mind-barrier in mathematics using formal verification \nAbstract: In this talk I will argue that formal verification helps break the one-mind-barrier in mathematics. Indeed\, formal verification allows a team of mathematicians to collaborate on a project\, without one person understanding all parts of the project. At the same time\, it also allows a mathematician to rapidly free mental RAM in order to work on a different component of a project. It thus also expands the one-mind-barrier. \nI will use the Liquid Tensor Experiment as an example\, to illustrate the above two points. This project recently finished the formalization of the main theorem of liquid vector spaces\, following up on a challenge by Peter Scholze. \nVideo
URL:https://cmsa.fas.harvard.edu/event/breaking-the-one-mind-barrier-in-mathematics-using-formal-verification/
LOCATION:CMSA Room G10\, CMSA\, 20 Garden Street\, Cambridge\, MA\, 02138\, United States
CATEGORIES:New Technologies in Mathematics Seminar
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20220415T090000
DTEND;TZID=America/New_York:20220415T130000
DTSTAMP:20260515T141950
CREATED:20230705T083343Z
LAST-MODIFIED:20240229T102446Z
UID:10000088-1650013200-1650027600@cmsa.fas.harvard.edu
SUMMARY:Workshop on Machine Learning and Mathematical Conjecture
DESCRIPTION:On April 15\, 2022\, the CMSA will hold a one-day workshop\, Machine Learning and Mathematical Conjecture\, related to the New Technologies in Mathematics Seminar Series. \nLocation: Room G10\, 20 Garden Street\, Cambridge\, MA 02138. \nOrganizers: Michael R. Douglas (CMSA/Stony Brook/IAIFI) and Peter Chin (CMSA/BU). \nMachine learning has driven many exciting recent scientific advances. It has enabled progress on long-standing challenges such as protein folding\, and it has helped mathematicians and mathematical physicists create new conjectures and theorems in knot theory\, algebraic geometry\, and representation theory. \nAt this workshop\, we will bring together mathematicians\, theoretical physicists\, and machine learning researchers to review the state of the art in machine learning\, discuss how ML results can be used to inspire\, test and refine precise conjectures\, and identify mathematical questions which may be suitable for this approach. \nSpeakers: \n\nJames Halverson\, Northeastern University Dept. of Physics and IAIFI\nFabian Ruehle\, Northeastern University Dept. of Physics and Mathematics and IAIFI\nAndrew Sutherland\, MIT Department of Mathematics\n\n  \n \n  \n  \n \n 
URL:https://cmsa.fas.harvard.edu/event/workshop-on-machine-learning-and-mathematical-conjecture/
LOCATION:CMSA Room G10\, CMSA\, 20 Garden Street\, Cambridge\, MA\, 02138\, United States
CATEGORIES:Event,Workshop
ATTACH;FMTTYPE=image/png:https://cmsa.fas.harvard.edu/media/Machine-Learning.png
END:VEVENT
END:VCALENDAR