pilancilab Goto Github PK

1d-convex-nn

adaptive-newton-sketch

adaptive_effdim_solver

Companion code for the paper "Fast Convex Quadratic Optimization Solvers with Adaptive Sketching-based Preconditioners"

caldera

Compressing Large Language Models using Low Precision and Low Rank Decomposition

convex_autoencoder

Two-Layer ReLU Autoencoders via Convex Optimization based on the paper "Convex Neural Autoregressive Models: Towards Tractable, Expressive, and Theoretically-Backed Models for Sequential Forecasting and Generation" by B. Bartan, T. Ergen, M. Pilanci

convex_nn

ihs-bin

matrix-compressor

Implementation of LPLR algorithm for matrix compression

neural-recovery

nfda

poly_act_convex_nn

randomized-geometric-algebra-methods-for-convex-neural-networks

relu_optimal_sets

Code to replicate experiments in the paper Optimal Sets and Solution Paths of ReLU Networks by Aaron Mishkin and Mert Pilanci.

riemannian_preconditioned_lora

source code for paper "Riemannian Preconditioned LoRA for Fine-Tuning Foundation Models"

scnn

Scalable Convex Neural Networks

scnn_experiments

Code to replicate experiments in https://arxiv.org/abs/2202.01331.

threshold-networks