Thomas Pethick
10 papers · 2021–2025 · 3 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 ↓+2 more ↓ Show less ↑
π Interdisciplinary Bridge Β· Bronze π Conference Polyglot Β· Bronze πΊοΈ Taxonomy Completionist (18) π€ Dynamic Duo (10) π Century Club Β· Bronze
π₯
Unstoppable Β· Bronze
ποΈ
Keyword Collector
(51)
Venues
Top co-authors
Research topics
Keywords
variational inequality
(4)
extragradient method
(2)
non-convex optimization
(2)
global convergence
(2)
first-order method
(2)
sharpness-aware minimization
(2)
convergence analysis
(1)
parallel computing
(1)
neural network training
(1)
loss landscape
(1)
convergence rate
(1)
dual averaging
(1)
gradient computation
(1)
deep architecture
(1)
neural network optimization
(1)
convergence guarantee
(1)
0-1 loss
(1)
bilevel optimization
(1)
linear convergence
(1)
adversarial training
(1)
Papers
Efficient Interpolation between Extragradient and Proximal Methods for Weak MVIs
ICLR 2025
Training Deep Learning Models with Norm-Constrained LMOs
ICML 2025
Improving SAM Requires Rethinking its Optimization Formulation
ICML 2024
SAMPa: Sharpness-aware Minimization Parallelized
NeurIPS 2024
Finding Actual Descent Directions for Adversarial Training
ICLR 2023
Solving stochastic weak Minty variational inequalities without increasing batch size
ICLR 2023
Stable Nonconvex-Nonconcave Training via Linear Interpolation
NeurIPS 2023
Escaping limit cycles: Global convergence for constrained nonconvex-nonconcave minimax problems
ICLR 2022
Sifting through the noise: Universal first-order methods for stochastic variational inequalities
NeurIPS 2021
Subquadratic Overparameterization for Shallow Neural Networks
NeurIPS 2021