2 citations · 2 across the 5 of their papers we have counts for
4 papers · 1 filter
When Are Two SAE Latents the Same Feature?
Alexandra Suvorikova, Ilgam Latypov, Anton Trukhan +1
Comparing sparse autoencoders (SAEs) requires connecting feature correspondence, differences between whole dictionaries, and uncertainty from finite evaluation data. We develop a f…
Clipped or Unclipped? Finite-Sample Trade-offs for Averaged SGD under Heavy-Tailed Noise
Alexandra Suvorikova, Egor Gladin, Darina Dvinskikh +5
Gradient clipping is widely used to stabilize training, but it need not improve the statistical accuracy of averaged SGD, even under heavy-tailed noise. We derive a finite-sample c…
Managing Self-Learning Experts under Per-Round Budget Constraints
Ilgam Latypov, Alexandra Suvorikova, Alexey Kroshnin +2
This paper addresses the problem of sequential decision-making under learning budget constraints. Such settings naturally arise in applications like managing a portfolio of bandit…
Implicitly normalized forecaster with clipping for linear and non-linear heavy-tailed multi-armed bandits
Yuriy Dorn, Nikita Kornilov, Nikolay Kutuzov +3
The Implicitly Normalized Forecaster (INF) algorithm is considered to be an optimal solution for adversarial multi-armed bandit (MAB) problems. However, most of the existing comple…