Events

In Spring 2023, the seminar took place on Wednesdays from 11:30am to 12:30pm in Blocker 220.

• September 06 in Blocker 302: Loss functions for finite sets, by Suhan Zhong (Texas A&M University, Mathematics)

• September 20: Linear algebra at work: machine learning and cybersecurity, by Mike Michailidis (MathWorks)

• October 04: Interplay between generalization and optimization via algorithmic stability, by Yiming Ying (University at Albany, Mathematics and Statistics)

• October 18: A Trustworthy Learning Theory? The View from Optimal Recovery, by Simon Foucart (Texas A&M University, Mathematics)

• November 01: Joint spectral clustering in multilayer network data, by Jesús Arroyo Relión (Texas A&M University, Statistics)

• November 15 in Blocker 302: Distribution-free deviation bounds of learning via model selection with cross-validation risk estimation, by Diego Marcondes (University of São Paulo, Computer Science)

• Friday November 17 at 1:50pm in Blocker 304 (joint with Mathematical Physics and Harmonic Analysis): Control and Machine Learning, by Enrique Zuazua (Friedrich-Alexander-Universität Erlangen-Nürnberg, Data Science)

In Spring 2023, the seminar took place on Wednesdays from 11:30am to 12:30pm in Blocker 220.

• January 25 in Blocker 302: Optimal nonlinear approximation and data-based reconstruction, by Albert Cohen (Sorbonne University, Mathematics)

• February 08: Counter examples for (stochastic) gradient descent, by Vivak Patel (University of Wisconsin-Madison, Statistics)

• February 15: Rigorous analysis and numerical implementation of nudging data assimilation algorithms, by Edriss Titi (University of Cambridge and Texas A&M University, Mathematics)

• March 08: Optimization and generalization for self-supervised learning, by Tianbao Yang (Texas A&M University, Computer Science and Engineering)

• March 22: Data-driven methods for neural network quantization with error guarantees, by Rayan Saab (University of California San Diego, Mathematics, Halicioglu Data Science Institute)

• April 05: Some computational aspects of wave turbulence, by Minh-Binh Tran (Texas A&M University, Mathematics)

• April 26: Efficient numerical methods for optimal control problems governed by geodesic flows of diffeomorphisms, by Andreas Mang (University of Houston, Mathematics )

In Fall 2022, the seminar took place on Wednesdays from 11:30am to 12:30pm in Blocker 220.

• August 31: Non-linear dictionary approximation and applications to learning algorithms, by Jonathan Siegel (Texas A&M University, Mathematics)

• September 14: Approximation via neural networks, by Guergana Petrova (Texas A&M University, Mathematics)

• September 21: Learning from very few samples, by P. R. Kumar (Texas A&M University, Electrical and Computer Engineering)

• October 05 in Blocker 302: Control and machine learning, by Enrique Zuazua (Friedrich-Alexander-Universität Erlangen-Nürnberg, Data Science)

• October 19: Low-distortion embeddings of submanifolds of Rn: lower bounds, faster realizations, and applications, by Mark Iwen (Michigan State University, Mathematics)

• November 09: Three uses of semidefinite programming in Approximation Theory, by Simon Foucart (Texas A&M University, Mathematics)

• November 16: Model-form uncertainty for epidemic models, by Nick Hengartner (Los Alamos National Laboratory, Center for Nonlinear Studies)

• November 30: Side-effects of learning from low dimensional data embedded in an Euclidean space, by Richard Tsai (University of Texas-Austin, Mathematics)

 In Spring 2022, the seminar took place on Wednesdays from 11:30am to 12:30pm in Blocker 302.

• January 26: Continuous time stochastic gradient descent and flat minimum selection by Stephan Wojtowytsch (Texas A&M University, Mathematics).

• February 09: Memory-efficient projection methods for metric-constrained optimization by Nate Veldt (Texas A&M University, Computer Science and Engineering).

• February 23: Optimal recovery in Hilbert spaces from exact or inaccurate data by Chunyang Liao (Texas A&M University, Mathematics).

• March 23: Double-matched matrix decomposition for multi-view data by Irina Gaynanova (Texas A&M University, Statistics).

• April 06: Approximation and optimization via neural networks by Josiah Park (Texas A&M University, Mathematics).

• April 20: Approximation properties of Gaussian process regression by Rui Tuo (Texas A&M University, Industrial and Systems Engineering)

In Fall 2021, the seminar took place on Wednesdays from 11:30am to 12:30pm in Blocker 506A.

• September 01: Thoughts on Deep Learning  by Ronald DeVore (Texas A&M University, Mathematics).

• September 15: Near-best adaptive piecewise-polynomial approximations  by Peter Binev (University of South Carolina, Mathematics).

• September 29: Self-adaptive physics-informed neural networks by Ulisses Braga-Neto (Texas A&M University, Electrical and Computer Engineering).

• October 11: Mathematical methods for privacy-preserving machine learning by Thomas Strohmer (University of California Davis, Mathematics).

• October 27: Numerically-stable coded distributed computing: an overview and some recent results by Anoosheh Heidarzadeh (Texas A&M University, Electrical and Computer Engineering).

• November 17: Machine learning of collective behaviors from observations by Ming Zhong (Texas A&M University, TAMIDS). 

• October 11th, 2021: CAMDA/TAMIDS Seminar (Virtual): Thomas Strohmer (UC Davis)

• October 30th, 2020: CAMDA/TAMIDS Seminar (Virtual): Justin Romberg (Georgia Tech)