We bound the excess risk of interpolating deep linear networks trained u...
While a broad range of techniques have been proposed to tackle distribut...
In this work, we provide a characterization of the feature-learning proc...
Benign overfitting, the phenomenon where interpolating models generalize...
Importance weighting is a classic technique to handle distribution shift...
We prove a lower bound on the excess risk of sparse interpolating proced...
The recent success of neural network models has shone light on a rather
...
We study a theory of reinforcement learning (RL) in which the learner
re...
We establish conditions under which gradient descent applied to fixed-wi...
We study the training of finite-width two-layer smoothed ReLU networks f...
We prove bounds on the population risk of the maximum margin algorithm f...
We consider the problem of sampling from a strongly log-concave density ...
We study the phenomenon that some modules of deep neural networks (DNNs)...
Langevin Monte Carlo (LMC) is an iterative algorithm used to generate sa...
We consider the stochastic linear (multi-armed) contextual bandit proble...
We study the problem of sampling from a distribution where the negative
...
We present a generalization of the adversarial linear bandits framework,...
We provide convergence guarantees in Wasserstein distance for a variety ...
We present theoretical guarantees for an alternating minimization algori...
We study the underdamped Langevin diffusion when the log of the target
d...