18 papers
Active Inference as Context Acquisition for AI Agents
Sanchayan Dutta, Sai Niranjan Ramachandran, Suvrit Sra
Interactive AI agents must acquire the right context as efficiently as possible. When a user omits a constraint, preference, file, or task variable, an agent can proceed with a def…
An Algebraic Matrix Spencer Theorem
Emrullah Akbas, Suvrit Sra
We develop an algebraic approach to matrix discrepancy based on the representation theory of finite-dimensional C-algebras. As an application, we resolve a substantial structur…
Free Heavy-Tailed Lunch for Muon: A Theoretical Justification of Empirical Success
Florian Hübler, Thomas Pethick, Suvrit Sra
Non-Euclidean optimisation methods with matrix-valued updates, such as Muon and Scion, have recently shown strong empirical performance for training Transformer models, yet their t…
Trees to Flows and Back: Unifying Decision Trees and Diffusion Models
Sai Niranjan Ramachandran, Suvrit Sra
Decision trees and diffusion models are ostensibly disparate model classes, one discrete and hierarchical, the other continuous and dynamic. This work unifies the two by establishi…
A projection-based framework for gradient-free and parallel learning
Andreas Bergmeister, Manish Krishan Lal, Stefanie Jegelka +1
We present a feasibility-seeking approach to neural network training. This mathematical optimization framework is distinct from conventional gradient-based loss minimization and us…
Tight Generalization Bounds for Noiseless Inverse Optimization
Pouria Fatemi, Hoomaan Maskan, Suvrit Sra +1
Inverse optimization (IO) seeks to infer the parameters of a decision-maker's objective from observed context--action data. We study noiseless IO, where demonstrations are generate…