7 papers
Machine-learnable Sets
Veit Elser, Manish Krishan Lal
In this study we present a formal definition of large discrete sets having, informally, three properties: their elements are easily recognized, easily generated, and the latter tas…
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…
Backpropagation from KL Projections: Differential and Exact I-Projection Correspondences
Manish Krishan Lal
We establish two correspondences between reverse-mode automatic differentiation (backpropagation at a given forward-pass point) and compositions of projection maps in Kullback--Lei…
Learning with Boolean threshold functions
Veit Elser, Manish Krishan Lal
We develop a method for training neural networks on Boolean data in which the values at all nodes are strictly , and the resulting models are typically equivalent to network…
The Flow-Limit of Reflect-Reflect-Relax: Existence, Stability, and Discrete-Time Behavior
Manish Krishan Lal
We study the Reflect-Reflect-Relax (RRR) algorithm in its small-step (flow-limit) regime. In the smooth transversal setting, we show that the transverse dynamics form a hyperbolic…
Cross-fluctuation phase transitions reveal sampling dynamics in diffusion models
Sai Niranjan Ramachandran, Manish Krishan Lal, Suvrit Sra
We analyse how the sampling dynamics of distributions evolve in score-based diffusion models using cross-fluctuations, a centered-moment statistic from statistical physics. Specifi…