Topics in Deep Learning Theory
CMSA Room G10 CMSA, 20 Garden Street, Cambridge, MA, United StatesTopics in Deep Learning Theory Eli Grigsby
Loading view.
Math and Machine Learning Program Open Discussion/Tea
Common Room, CMSA 20 Garden Street, Cambridge, MA, United StatesOpen Discussion/Tea
Topological Invariants of gapped states through cosheaves
Science Center Hall E 1 Oxford Street, Cambridge, MA, United StatesGeometry and Quantum Theory Seminar Speaker: Bowen Yang, Harvard CMSA Title: Topological Invariants of gapped states through cosheaves Abstract: We provide a proper mathematical framework for the constructions of topological invariants of gapped quantum states and interpret topological invariants of gapped states as lattice analogs of ’t Hooft anomalies in Quantum Field Theory. Our secondary […]
Math and Machine Learning Program Discussion
CMSA Room G10 CMSA, 20 Garden Street, Cambridge, MA, United StatesMath and Machine Learning Program Discussion
CMSA Q&A Seminar: Cliff Taubes
CMSA Q&A Seminar Speaker: Cliff Taubes, Harvard Mathematics Topic: What are Z/2 harmonic 1-forms?
Hierarchical data structures through the lenses of diffusion models
CMSA Room G10 CMSA, 20 Garden Street, Cambridge, MA, United Stateshttps://youtu.be/x7LPDDYZn94 New Technologies in Mathematics Seminar Speaker: Antonio Sclocchi, EPFL Title: Hierarchical data structures through the lenses of diffusion models Abstract: The success of deep learning with high-dimensional data relies on the fact that natural data are highly structured. A key aspect of this structure is hierarchical compositionality, yet quantifying it remains a challenge. In […]
Enumerative geometry and modularity in two-modulus K3-fibered Calabi-Yau threefolds
CMSA Room G10 CMSA, 20 Garden Street, Cambridge, MA, United StatesMathematical Physics and Algebraic Geometry Seminar Speaker: Chuck Doran, Harvard CMSA Title: Enumerative geometry and modularity in two-modulus K3-fibered Calabi-Yau threefolds Abstract: Smooth $M_m$-polarized K3-fibered Calabi-Yau (CY) 3-folds have been classified in terms of the choice of a generalized functional invariant and, in the case $m=1$, a generalized homological invariant. The resulting geometries generally exhibit […]
Holography and Regge Phases at Large U(1) Charge
CMSA Room G10 CMSA, 20 Garden Street, Cambridge, MA, United StatesQuantum Field Theory and Physical Mathematics Seminar Speaker: Giulia Fardelli, Boston University Title: Holography and Regge Phases at Large U(1) Charge Abstract: A single Conformal Field Theory (CFT) can have a rich phase diagram with qualitatively different emergent behaviors in a range of different regimes parameterized by the conserved charges of the theory. In this […]
Math and Machine Learning Program Discussion
CMSA Room G10 CMSA, 20 Garden Street, Cambridge, MA, United StatesMath and Machine Learning Program Discussion
High-dimensional learning of narrow neural networks
CMSA Room G10 CMSA, 20 Garden Street, Cambridge, MA, United StatesMember Seminar Speaker: Hugo Cui, CMSA Title: High-dimensional learning of narrow neural networks Abstract: This talk explores the interplay between neural network architectures and data structure through the lens of high-dimensional asymptotics. We focus on a class of narrow neural networks, namely networks possessing a finite number of hidden units, while operating in high dimensions. In the […]
Math and Machine Learning Program Discussion
CMSA Room G10 CMSA, 20 Garden Street, Cambridge, MA, United StatesMath and Machine Learning Program Discussion
Local complexity measures in modern parameterized function classes for supervised learning
CMSA Room G10 CMSA, 20 Garden Street, Cambridge, MA, United StatesColloquium Speaker: Elisenda Grigsby, Boston College Title: Local complexity measures in modern parameterized function classes for supervised learning Abstract: The parameter space for any fixed architecture of neural networks serves as a proxy during training for the associated class of functions - but how faithful is this representation? For any fixed feedforward ReLU network architecture, it […]