Mar 26 4:00 pm - 5:00 pm (Remote) A mean-field theory of lazy training in two-layer neural nets: entropic regularization and controlled McKean-Vlasov dynamics
Apr 9 4:00 pm - 5:00 pm CANCELED: Communication-Efficient and Straggler-Resilient Distributed Learning
Oct 1 4:00 pm - 5:00 pm Discrete choice with irrelevant alternatives: models and lower bounds on testing
Feb 18 4:00 pm - 5:00 pm A Lyapunov Theory for Finite-Sample Guarantees of Asynchronous, Value-Based Reinforcement Learning Algorithms
Apr 1 4:00 pm - 5:00 pm Simple Agent, Complex Environment: Efficient Reinforcement Learning with Agent State
Sep 2 4:00 pm - 5:00 pm Multiclass and Multi-Label Learning with General Losses: What is the Right Output Coding and Decoding?
Oct 21 11:00 am - 12:00 pm Communication and Sensing: From Compressed Sampling to Model-based Deep Learning
Jan 6 4:00 pm - 5:00 pm Data-driven and Learning-based Methods for Control: Challenges and New Horizons
Oct 13 4:00 pm - 5:00 pm Method of Moments: From Sample Complexity to Efficient Implicit Computations
Oct 27 4:00 pm - 5:00 pm Accelerating Ill-conditioned Low-rank Estimation via Scaled Gradient Descent
Feb 9 9:15 am - 10:15 am Understanding the Universality Phenomenon in High- Dimensional Estimation and Learning: Some Recent Progress
Feb 23 9:15 am - 10:15 am Cancelled: Implicit Geometry of Large Classification Models: Imbalance Trouble
Mar 21 10:00 am - 11:00 am Load Balancing under Data Locality: Extending Mean-Field Framework to Constrained Large-Scale Systems
Apr 6 9:15 am - 10:15 am Best of three worlds? Bias and extrapolation in constant-step size stochastic approximation
Sep 7 3:30 pm - 5:00 pm On the Emergence of Invariant Low-Dimensional Subspaces in Gradient Descent for Learning Deep Networks
Sep 22 3:30 pm - 5:00 pm Integrated Sensing and Communication: aspects from Information Theory, Communication Theory, and Machine Learning
Sep 28 3:30 pm - 5:00 pm Solving Inverse Problems with Latent Diffusion Models via Hard Data Consistency
Oct 12 3:30 pm - 5:00 pm Theoretical Characterization of Forgetting and Generalization of Continual Learning
Oct 26 3:30 pm - 5:00 pm Breaking the Sample Size Barrier in Reinforcement Learning via Model-Based Algorithms
Nov 2 3:30 pm - 5:00 pm Overparameterization and Global Optimality in Nonconvex Low-Rank Matrix Estimation and Optimization
Nov 30 3:30 pm - 5:00 pm (CANCELED) Discrete Optimization for Adversarial Attacks on Large Language Models
Dec 8 3:30 pm - 4:30 pm Towards a Theoretical Understanding of Parameter-Efficient Fine-Tuning (and Beyond)