
Foolish Crowds Support Benign Overfitting
We prove a lower bound on the excess risk of sparse interpolating proced...
read it

The Interplay Between Implicit Bias and Benign Overfitting in TwoLayer Linear Networks
The recent success of neural network models has shone light on a rather ...
read it

On the Theory of Reinforcement Learning with OnceperEpisode Feedback
We study a theory of reinforcement learning (RL) in which the learner re...
read it

When does gradient descent with logistic loss interpolate using deep networks with smoothed ReLU activations?
We establish conditions under which gradient descent applied to fixedwi...
read it

When does gradient descent with logistic loss find interpolating twolayer networks?
We study the training of finitewidth twolayer smoothed ReLU networks f...
read it

Finitesample analysis of interpolating linear classifiers in the overparameterized regime
We prove bounds on the population risk of the maximum margin algorithm f...
read it

Oracle lower bounds for stochastic gradient sampling algorithms
We consider the problem of sampling from a strongly logconcave density ...
read it

The intriguing role of module criticality in the generalization of deep networks
We study the phenomenon that some modules of deep neural networks (DNNs)...
read it

Langevin Monte Carlo without Smoothness
Langevin Monte Carlo (LMC) is an iterative algorithm used to generate sa...
read it

OSOM: A Simultaneously Optimal Algorithm for MultiArmed and Linear Contextual Bandits
We consider the stochastic linear (multiarmed) contextual bandit proble...
read it

Sharp Convergence Rates for Langevin Dynamics in the Nonconvex Setting
We study the problem of sampling from a distribution where the negative ...
read it

Online learning with kernel losses
We present a generalization of the adversarial linear bandits framework,...
read it

On the Theory of Variance Reduction for Stochastic Gradient Monte Carlo
We provide convergence guarantees in Wasserstein distance for a variety ...
read it

Alternating minimization for dictionary learning with random initialization
We present theoretical guarantees for an alternating minimization algori...
read it

Underdamped Langevin MCMC: A nonasymptotic analysis
We study the underdamped Langevin diffusion when the log of the target d...
read it
Niladri S. Chatterji
is this you? claim profile