5 papers
Learning to Think from Multiple Thinkers
Nirmit Joshi, Roey Magen, Nathan Srebro +2
We study learning with Chain-of-Thought (CoT) supervision from multiple thinkers, all of whom provide correct but possibly systematically different solutions, e.g., step-by-step so…
OpenApps: Simulating Environment Variations to Measure UI-Agent Reliability
Karen Ullrich, Jingtong Su, Claudia Shi +7
Reliability is key to realizing the promise of autonomous UI-Agents, multimodal agents that directly interact with apps in the same manner as humans, as users must be able to trust…
How Reinforcement Learning After Next-Token Prediction Facilitates Learning
Nikolaos Tsilivis, Eran Malach, Karen Ullrich +1
Recent advances in reasoning domains with neural networks have primarily been enabled by a training recipe that optimizes Large Language Models, previously trained to predict the n…
On the Geometry of Regularization in Adversarial Training: High-Dimensional Asymptotics and Generalization Bounds
Matteo Vilucchio, Nikolaos Tsilivis, Bruno Loureiro +1
Regularization, whether explicit in terms of a penalty in the loss or implicit in the choice of algorithm, is a cornerstone of modern machine learning. Indeed, controlling the comp…
Flavors of Margin: Implicit Bias of Steepest Descent in Homogeneous Neural Networks
Nikolaos Tsilivis, Eitan Gronich, Julia Kempe +1
We study the implicit bias of the general family of steepest descent algorithms with infinitesimal learning rate in deep homogeneous neural networks. We show that: (a) an algorithm…