Mert Pilanci

CL-DPS: A Contrastive Learning Approach to Blind Nonlinear Inverse Problem Solving via Diffusion Posterior Sampling

A Recovery Guarantee for Sparse Neural Networks

ASMIL: Attention-Stabilized Multiple Instance Learning for Whole-Slide Imaging

Exponential Low-Rank Adapters

MatRL: Provably Generalizable Iterative Algorithm Discovery via Monte-Carlo Tree Search

COALA: Convex Optimization for Alignment and Preference Learning on a Single GPU

CLARA: Convex Low-resource Accent-Robust Language Detection in ASR

Exploring The Loss Landscape Of Regularized Neural Networks Via Convex Duality

Geometric Algebra Planes: Convex Implicit Neural Volumes

Newton Meets Marchenko-Pastur: Massively Parallel Second-Order Optimization with Hessian Sketching and Debiasing

Geometric Algebra Planes: Convex Implicit Neural Volumes

Reinforcement Learning and Heuristics for Hardware-Efficient Constrained Code Design

SERDES Link Training with Edge Inference: Neural-Network Driven Discrete Optimization to Maximize Link Efficiency

Active Learning of Deep Neural Networks via Gradient-Free Cutting Planes

Adaptive Inference: Theoretical Limits and Opportunities for Efficient AI

Adversarial Training of Two-Layer Polynomial and ReLU Activation Networks via Convex Optimization

Black Boxes and Looking Glasses: Multilevel Symmetries, Reflection Planes, and Convex Optimization in Deep Networks

Active Learning of Deep Neural Networks via Gradient-Free Cutting Planes

Scalable Preference Learning for Large Language Models via Convex Optimization

Convex Distillation: Efficient Compression of Deep Networks via Convex Optimization