conftrace_

low-rank factorization

26 papers

Explore in graph

Co-occurring keywords

model compression (3302) matrix completion (356) matrix factorization (529) non-convex optimization (547) stochastic gradient descent (1091) low-rank approximation (323) knowledge distillation (3725) parameter reduction (97) latent space (854) singular value decomposition (222)

Papers

GLEN: Generalized Focal Loss Ensemble of Low-Rank Networks for Calibrated Visual Question Answering AAAI 2025
Integrating Independent Layer-Wise Rank Selection with Low-Rank SVD Training for Model Compression: A Theory-Driven Approach IJCAI 2025
Low-Rank Prune-And-Factorize for Language Model Compression COLING 2024
Single-Model and Any-Modality for Video Object Tracking CVPR 2024
Differentially Private Matrix Completion through Low-rank Matrix Factorization AISTATS 2023
Convergence of Alternating Gradient Descent for Matrix Factorization NIPS 2023
LightFormer: Light-weight Transformer Using SVD-based Weight Transfer and Parameter Sharing ACL 2023
Exploiting Explainable Metrics for Augmented SGD CVPR 2022
Temporal Knowledge Graph Reasoning with Low-rank and Model-agnostic Representations ACL 2022
ROSITA: Refined BERT cOmpreSsion with InTegrAted techniques AAAI 2021
Low-Rank Sinkhorn Factorization ICML 2021
Low-Rank Subspaces in GANs NIPS 2021
Shapeshifter: a Parameter-efficient Transformer using Factorized Reshaped Matrices NIPS 2021
Structured Pruning of Large Language Models EMNLP 2020
Compact Speaker Embedding: lrx-Vector INTERSPEECH 2020
The k-tied Normal Distribution: A Compact Parameterization of Gaussian Mean Field Posteriors in Bayesian Neural Networks ICML 2020
Cascaded Projection: End-To-End Network Compression and Acceleration CVPR 2019
Rate Distortion For Model Compression:From Theory To Practice ICML 2019
Model-based targeted dimensionality reduction for neuronal population data NIPS 2018
Finding Global Optima in Nonconvex Stochastic Semidefinite Optimization with Variance Reduction AISTATS 2018
The Price of Privacy for Low-rank Factorization NIPS 2018
High resolution neural connectivity from incomplete tracing data using nonnegative spline regression NIPS 2016
The non-convex Burer-Monteiro approach works on smooth semidefinite programs NIPS 2016
Sub-sampled Newton Methods with Non-uniform Sampling NIPS 2016
Model Compression Applied to Small-Footprint Keyword Spotting INTERSPEECH 2016