|
Poster
|
Wed 11:00
|
Taming Heavy-Tailed Losses in Adversarial Bandits and the Best-of-Both-Worlds Setting
Duo Cheng · Xingyu Zhou · Bo Ji
|
|
|
Poster
|
Wed 16:30
|
Catastrophic Goodhart: regularizing RLHF with KL divergence does not mitigate heavy-tailed reward misspecification
Thomas Kwa · Drake Thomas · Adrià Garriga-Alonso
|
|
|
Poster
|
Thu 16:30
|
Heavy-Tailed Class Imbalance and Why Adam Outperforms Gradient Descent on Language Models
Frederik Kunstner · Alan Milligan · Robin Yadav · Mark Schmidt · Alberto Bietti
|
|
|
Poster
|
Wed 11:00
|
Near-Optimal Streaming Heavy-Tailed Statistical Estimation with Clipped SGD
Aniket Das · Dheeraj Nagaraj · Soumyabrata Pal · Arun Suggala · Prateek Varshney
|
|
|
Poster
|
Fri 11:00
|
AlphaPruning: Using Heavy-Tailed Self Regularization Theory for Improved Layer-wise Pruning of Large Language Models
Haiquan Lu · Yefan Zhou · Shiwei Liu · Zhangyang "Atlas" Wang · Michael Mahoney · Yaoqing Yang
|
|
|
Poster
|
Fri 16:30
|
A Separation in Heavy-Tailed Sampling: Gaussian vs. Stable Oracles for Proximal Samplers
Ye He · Alireza Mousavi-Hosseini · Krishnakumar Balasubramanian · Murat Erdogdu
|
|
|
Workshop
|
|
Heavy-Tailed Class Imbalance and Why Adam Outperforms Gradient Descent on Language Models
Frederik Kunstner · Robin Yadav · Alan Milligan · Mark Schmidt · Alberto Bietti
|
|
|
Workshop
|
|
From Gradient Clipping to Normalization for Heavy Tailed SGD
Florian Hübler · Ilyas Fatkhullin · Niao He
|
|
|
Poster
|
Fri 16:30
|
Emergence of heavy tails in homogenized stochastic gradient descent
Zhezhe Jiao · Martin Keller-Ressel
|
|
|
Poster
|
Wed 11:00
|
Private Stochastic Convex Optimization with Heavy Tails: Near-Optimality from Simple Reductions
Hilal Asi · Daogao Liu · Kevin Tian
|
|
