activity
20242026
collaborators

7 papers

cs.LG2026

When Can Safe Controllers Adapt? Information before Commitment

Venkatesh Saligrama

Safe adaptive control is online adaptation under a safety guarantee on the learning trajectory itself. The controller may use any causal, history-dependent rule and act differently…

cs.LG2026

Data Deletion Can Help in Adaptive RL

Param Budhraja, Aditya Gangrade, Alex Olshevsky +1

Deploying reinforcement learning policies in the real world requires adapting to time-varying environments. We study this problem in the contextual Markov Decision Process (cMDP) f…

cs.LG2026

Symmetry Reveals Layerwise Dynamics: How Transformers Perform In-Context Classification

Patrick Lutz, Themistoklis Haris, Arjun Chandra +2

Transformers can perform in-context classification from a few labeled examples, yet the inference-time algorithm remains opaque. We study multi-class linear classification in the h…

cs.LG2025

Linear Transformers Implicitly Discover Unified Numerical Algorithms

Patrick Lutz, Aditya Gangrade, Hadi Daneshmand +1

We train a linear attention transformer on millions of masked-block matrix completion tasks: each prompt is masked low-rank matrix whose missing block may be (i) a scalar predictio…

cs.LG2025

Constrained Linear Thompson Sampling

Aditya Gangrade, Venkatesh Saligrama

We study safe linear bandits (SLBs), where an agent selects actions from a convex set to maximize an unknown linear objective subject to unknown linear constraints in each round. E…

cs.CV2024

Deep Companion Learning: Enhancing Generalization Through Historical Consistency

Ruizhao Zhu, Venkatesh Saligrama

We propose Deep Companion Learning (DCL), a novel training method for Deep Neural Networks (DNNs) that enhances generalization by penalizing inconsistent model predictions compared…