
The Deep Bootstrap: Good Online Learners are Good Offline Generalizers
We propose a new framework for reasoning about generalization in deep le...
read it

Distributional Generalization: A New Kind of Generalization
We introduce a new notion of generalization – Distributional Generalizat...
read it

Learning Rate Annealing Can Provably Help Generalization, Even for Convex Problems
Learning rate schedule can significantly affect generalization performan...
read it

Optimal Regularization Can Mitigate Double Descent
Recent empirical and theoretical studies have shown that many learning a...
read it

More Data Can Hurt for Linear Regression: Samplewise Double Descent
In this expository note we describe a surprising phenomenon in overparam...
read it

Deep Double Descent: Where Bigger Models and More Data Hurt
We show that a variety of modern deep learning tasks exhibit a "doubled...
read it

SGD on Neural Networks Learns Functions of Increasing Complexity
We perform an experimental study of the dynamics of Stochastic Gradient ...
read it

Adversarial Robustness May Be at Odds With Simplicity
Current techniques in machine learning are so far are unable to learn cl...
read it

Algorithmic Polarization for Hidden Markov Models
Using a mild variant of polar codes we design linear compression schemes...
read it

The Generic Holdout: Preventing FalseDiscoveries in Adaptive Data Science
Adaptive data analysis has posed a challenge to science due to its abili...
read it

Tracking the ℓ_2 Norm with Constant Update Time
The ℓ_2 tracking problem is the task of obtaining a streaming algorithm ...
read it

General Strong Polarization
Arı kan's exciting discovery of polar codes has provided an altogether n...
read it

Predicting Positive and Negative Links with Noisy Queries: Theory & Practice
Social networks and interactions in social media involve both positive a...
read it
Preetum Nakkiran
is this you? claim profile