Courtney Paquette | DeepAI

AI Chat

Featured Co-authors

Julien Mairal
76 publications
Zaid Harchaoui
47 publications
Gauthier Gidel
46 publications
Fabian Pedregosa
29 publications
Jeffrey Pennington
28 publications
Dmitriy Drusvyatskiy
22 publications
Ben Adlam
16 publications
Damien Scieur
14 publications
Bart van Merriënboer
14 publications
Elliot Paquette
11 publications
Hongzhou Lin
9 publications

∙ 08/17/2023

Hitting the High-Dimensional Notes: An ODE for SGD learning dynamics on GLMs and multi-index models

We analyze the dynamics of streaming stochastic gradient descent (SGD) i...

0 Elizabeth Collins-Woodfin, et al. ∙

∙ 06/20/2022

Only Tails Matter: Average-Case Universality and Robustness in the Convex Regime

The recently developed average-case analysis of optimization methods all...

0 Leonardo Cunha, et al. ∙

∙ 06/15/2022

Implicit Regularization or Implicit Conditioning? Exact Risk Trajectories of SGD in High Dimensions

Stochastic gradient descent (SGD) is a pillar of modern machine learning...

0 Courtney Paquette, et al. ∙

∙ 06/02/2022

Trajectory of Mini-Batch Momentum: Batch Size Saturation and Convergence in High Dimensions

We analyze the dynamics of large batch stochastic gradient descent with ...

0 Kiwon Lee, et al. ∙

∙ 05/14/2022

Homogenization of SGD in high-dimensions: Exact dynamics and generalization properties

We develop a stochastic differential equation, called homogenized SGD, f...

0 Courtney Paquette, et al. ∙

∙ 06/07/2021

Dynamics of Stochastic Momentum Methods on Large-scale, Quadratic Models

We analyze a class of stochastic gradient algorithms with momentum on a ...

0 Courtney Paquette, et al. ∙

∙ 02/08/2021

SGD in the Large: Average-case Analysis, Asymptotics, and Stepsize Criticality

We propose a new framework, inspired by random matrix theory, for analyz...

0 Courtney Paquette, et al. ∙

∙ 06/08/2020

Halting Time is Predictable for Large Models: A Universality Property and Average-case Analysis

Average-case analysis computes the complexity of an algorithm averaged o...

8 Courtney Paquette, et al. ∙

∙ 03/23/2020

A termination criterion for stochastic gradient descent for binary classification

We propose a new, simple, and computationally inexpensive termination te...

0 Sina Baghal, et al. ∙

∙ 03/31/2017

Catalyst Acceleration for Gradient-Based Non-Convex Optimization

We introduce a generic scheme to solve nonconvex optimization problems u...

0 Courtney Paquette, et al. ∙

Are you a researcher?
Expose your work
to one of the largest
A.I. communities in the world