On August 2931, 2019 the Center of Mathematical Sciences and Applications will be hosting a workshop on Foundations of Computational Science. The workshop will be held in room G10 of the CMSA, located at 20 Garden Street, Cambridge, MA. This workshop is organized by David Xianfeng Gu.
Speakers:
Videos of the talks are contained in the Youtube playlist below. They can also be found through links in the schedule.
Thursday, August 29
Time  Speaker  Title/Abstract 

8:30 – 9:30am 
Breakfast 

9:30 – 9:40am 
Opening 

9:40 – 10:05am 
Tat Seng Chua 
Explainable AI and Multimedia Research
Abstract: AI as a concept has been around since the 1950’s. With the recent advancements in machine learning algorithms, and the availability of big data and large computing resources, the scene is set for AI to be used in many more systems and applications which will profoundly impact society. The current deep learning based AI systems are mostly in black box form and are often nonexplainable. Though it has high performance, it is also known to make occasional fatal mistakes. This has limited the applications of AI, especially in mission critical applications.
In this talk, I will present the current stateofthe arts in explainable AI, which holds promise to helping humans better understand and interpret the decisions made by the blackbox AI models. This is followed by our preliminary research on explainable recommendation, relation inference in videos, as well as leveraging prior domain knowledge, information theoretic principles, and adversarial algorithms to achieving explainable framework. I will also discuss future research towards quality, fairness and robustness of explainable AI. 
10:05 – 10:35am 
Group Photo and Coffee Break 

10:35 – 10:50am 
Maosong Sun 
Deep Learningbased Chinese Language Computation at Tsinghua University: Progress and Challenges 
10:50 – 11:05am 
Minlie Huang 
Controllable Text Generation 
11:05 – 11:20am 
Jun Liu 
Statistics Meets Neural Networks 
11:20 – 11:45am 
Yike Guo 
Data Efficiency in Machine Learning 
11:45 – 12:10pm 
Zuowei Shen 
Deep Approximation via Deep Learning
Abstract: The primary task of many applications is approximating/estimating a function through samples drawn from a probability distribution on the input space. The deep approximation is to approximate a function by compositions of many layers of simple functions, that can be viewed as a series of nested feature extractors. The key idea of deep learning network is to convert layers of compositions to layers of tunable parameters that can be adjusted through a learning process, so that it achieves a good approximation with respect to the input data. In this talk, we shall discuss mathematical foundation behind this new approach of approximation; how it differs from the classic approximation theory, and how this new theory can be applied to understand and design deep learning network. 
12:10 – 1:45pm 
Lunch 

1:45 – 2:00pm 
Wenwu Zhu 
Explainable media and network representation 
2:00 – 2:15pm 
Wee Sun Lee 
Neuralizing Algorithms
Abstract: Most interesting AI problems are computationally intractable to solve in the worst case. We argue that we should be solving AI problems for the typical or average case instead, and that machine learning provides a good set of tools to do so. We illustrate the approach on approximate inference algorithms on probabilistic graphical models using our recent works on factor graph neural networks and particle filter recurrent neural networks. 
2:15 – 2:30pm 
Jun Zhu 
Particlebased Inference for Bayesian deep learning 
2:30 – 3:00pm 
Coffee Break 

3:00 – 3:15pm 
Yuanchun Shi 
From Human Action Data To User Input Intention 
3:15 – 3:30pm 
Ke Deng 
Understanding complicated patterns of Chinese texts with very weak training 
3:30 – 4:00pm 
David Gu 
A Geometric View to Optimal Transportation and Generative Adversarial Models 
4:00 – 4:30pm 
Donald Rubin 
Relevant Statistical Evaluations When Comparing Procedures for Analyzing Data 
Friday, August 30
Time  Speaker  Title/Abstract 

8:30 – 9:00am 
Breakfast 

9:009:25am 
Qianxiao Li 
A meanfield optimal control formulation of deep learning
Abstract: In this talk, we discuss formulating, through a continuoustime approximation, deep supervised learning as a mean field optimal control problem. This allows us to derive necessary conditions for optimality in deep learning in the form of a meanfield Pontryagin’s maximum principle, as well as global characterizations of optimality using HamiltonJacobi Bellman equations. This forms a connection between deep learning on the one hand, and partial differential equations and the calculus of variations on the other. We also discuss interesting numerical algorithms and generalization estimates that can be derived from this viewpoint, as well as some results on function approximation using flows of dynamical systems. 
9:2510:15am 
Sarah Adel Bargal 
Grounding Deep Models for Improved Decision Making
Abstract: Deep models are stateoftheart for many computer vision tasks including object classification, action recognition, and captioning. As Artificial Intelligence systems that utilize deep models are becoming ubiquitous, it is becoming crucial to explain (ground) why they make certain decisions, and utilize such explanations (grounding) to further improve model performance. In this talk, I will present: (1) Frameworks in which grounding guides decisionmaking on the fly at test time by questioning whether the utilized evidence is ‘reasonable’, and during learning through the exploitation of new pathways in deep models. (2) A formulation that simultaneously grounds evidence in space and time, in a single pass, using topdown saliency. This visualizes the spatiotemporal cues that contribute to a deep recurrent neural network’s classification/captioning output. Based on these spatiotemporal cues, segments within a video that correspond with a specific action, or phrase from a caption, could be localized without explicitly optimizing/training for these tasks. 
10:1510:40am 
Xiaoqin Wang 
Encoding and decoding auditory information by the brain 
10:4011:00am 
Coffee Break 

11:0011:15am 
Hang Su 
Adversarial attacks in deep learning 
11:1511:30am 
Bin Xu 
AI Practice for Gaokao: Knowledge Graph Construction for Chinese K12 Education 
11:30 – 11:45am 
Liu Hanzhong 
Penalized regressionadjusted average treatment effect estimates in randomized experiments 
11:45 – 1:30pm 
Lunch 

1:30 – 2:15pm 
Cengiz Pehlevan 
Building sensory representations through learning 
2:15 – 3:00pm 
Sergiy Verstyuk 
Modeling economic time series using deep learning 
3:00 – 3:30pm 
Coffee 

3:30 – 4:15pm 
XiaoLi Meng 
Artificial Bayesian Monte Carlo Integration: A Practical Resolution to the Bayesian (Normalizing Constant) Paradox
Abstract: Advances in Markov chain Monte Carlo in the past 30 years have made Bayesian analysis a routine practice. However, there is virtually no practice of performing Monte Carlo integration from the Bayesian perspective; indeed, this problem has earned the “paradox” label in the context of computing normalizing constants (Wasserman, 2013). We first use the modelingwhatweignore idea of Kong et al. (2003) to explain that the crux of the paradox is not with the likelihood theory, which is essentially the same as for a standard nonparametric probability/density estimation (Vardi, 1985); though via using group theory, it provides a richer framework for modeling the tradeoff between statistical efficiency and computational efficiency. But there is a real Bayesian paradox: Bayesian analysis cannot be applied exactly for solving Bayesian computation, because to perform the exact Bayesian Monte Carlo integration would require more computation than needed to solve the original Monte Carlo problem. We then show that there is a practical resolution to this paradox using the profile likelihood obtained in Kong et al. (2006) and that this approximation is secondorder valid asymptotically. We also investigate a more computationally efficient approximation via an artificial likelihood of Geyer (1994). This artificial likelihood approach is only firstorder valid, but there is a computationally trivial adjustment to render its secondorder validity. We demonstrate empirically the efficiency of these approximated Bayesian estimators, compared to the usual frequentistbased Monte Carlo estimators, such as bridge sampling estimators (Meng and Wong, 1996). [This is a joint work with Masatoshi Uehara.] 
Saturday, August 31
Time  Speaker  Title/Abstract 

8:30 – 9:00am 
Breakfast 

9:00 – 9:45am 
Brian Kulis 
New Directions in Metric Learning
Abstract: Metric learning is a supervised machine learning problem concerned with learning a taskspecific distance function from supervised data. It has found numerous applications in problems such as similarity search, clustering, and ranking. Much of the foundational work in this area focused on the class of socalled Mahalanobis metrics, which may be viewed as Euclidean distances after linear transformations of the data. This talk will describe two recent directions in metric learning: deep metric learning and divergence learning. The first replaces the linear transformations with the output of a neural network, while the second considers a broader class than Mahalanobis metrics. I will discuss some of my recent work along both of these fronts, as well as ongoing attempts to combine these approaches together using a novel framework called deep divergences. 
9:45 – 10:30am 
Justin Solomon 
Linking the Theory and Practice of Optimal Transport
Abstract: Optimal transport is a theory linking probability to geometry, with applications across computer graphics, machine learning, and scientific computing. While transport has long been recognized as a valuable theoretical tool, only recently have we developed the computational machinery needed to apply it to practical computational problems. In this talk, I will discuss efforts with my students to scale up transport and related computations, showing that the best algorithm and model for this task depends on details of the application scenario. In particular, we will consider settings in representation learning using entropicallyregularized transport, Bayesian inference using semidiscrete transport, and graphics/PDE using dynamical Eulerian models. 
10:30 – 11:00am 
Coffee 

11:00 – 11:45am 
Mirac Suzgun 
Towards Understanding the Limitations of Deep Learning Models for Language 
11:45 – 1:15pm 
Lunch 

1:15pm – 2:00pm 
Jiafeng Chen & Suproteem Sarkar 
Robust and Extensible Deep Learning for Economic and Financial Applications 
2:00 – 2:45pm 
Scott Kominers 