activity
20172026
most citedTime Matters in Regularizing Deep Networks: Weight Decay and Data Augmentation Affect Early Learning Dynamics, Matter Little Near Convergence

21 citations · 45 across the 11 of their papers we have counts for

collaborators
Showing cs.AIShow all

2 papers · 1 filter

cs.AI2025

e1: Learning Adaptive Control of Reasoning Effort

Michael Kleinman, Matthew Trager, Alessandro Achille +2

Increasing the thinking budget of AI models can significantly improve accuracy, but not all questions warrant the same amount of reasoning. Users may prefer to allocate different a…

cs.AI2025

AI Agents as Universal Task Solvers

Alessandro Achille, Stefano Soatto

We describe AI agents as stochastic dynamical systems and frame the problem of learning to reason as in transductive inference: Rather than approximating the distribution of past d…