Elliot Paquette
8 papers · 2021–2025 · 4 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓
🌍
Conference Polyglot · Bronze
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(14)
❓
The Questioner
Venues
Top co-authors
Research topics
Keywords
stochastic gradient descent
(6)
least square
(3)
momentum method
(2)
random matrix theory
(2)
high-dimensional analysis
(2)
convergence rate
(2)
preconditioning
(1)
phase transition
(1)
implicit regularization
(1)
learning dynamics
(1)
gradient clipping
(1)
stochastic differential equation
(1)
generalization performance
(1)
nesterov acceleration
(1)
batch size
(1)
data complexity
(1)
heavy ball method
(1)
convex quadratic
(1)
model parameter
(1)
neural scaling law
(1)
Papers
Exact risk curves of signSGD in High-Dimensions: quantifying preconditioning and noise-compression effects
ICML 2025
To Clip or not to Clip: the Dynamics of SGD with Gradient Clipping in High-Dimensions
ICLR 2025
4+3 Phases of Compute-Optimal Neural Scaling Laws
NeurIPS 2024
The High Line: Exact Risk and Learning Rate Curves of Stochastic Adaptive Learning Rate Algorithms
NeurIPS 2024
Implicit Regularization or Implicit Conditioning? Exact Risk Trajectories of SGD in High Dimensions
NeurIPS 2022
Trajectory of Mini-Batch Momentum: Batch Size Saturation and Convergence in High Dimensions
NeurIPS 2022
Dynamics of Stochastic Momentum Methods on Large-scale, Quadratic Models
NeurIPS 2021
SGD in the Large: Average-case Analysis, Asymptotics, and Stepsize Criticality
COLT 2021