conftrace_

sparse model

83 papers

Explore in graph

Co-occurring keywords

model compression (3302) model pruning (237) mixture of expert (640) neural network pruning (265) feature selection (649) large language model (13587) sparse optimization (246) neural network (6616) convex optimization (1321) neural network optimization (1293)

Papers

Fast, Differentiable and Sparse Top-k: a Convex Analysis Perspective ICML 2023
Approximating Two-Layer Feedforward Networks for Efficient Transformers EMNLP 2023
Balanced Training for Sparse GANs NIPS 2023
CSTAR: Towards Compact and Structured Deep Neural Networks with Adversarial Robustness AAAI 2023
Beyond L1: Faster and Better Sparse Models with skglm NIPS 2022
How Well Do Sparse ImageNet Models Transfer? CVPR 2022
Robust Testing in High-Dimensional Sparse Models NIPS 2022
On the Identifiability of Nonlinear ICA: Sparsity and Beyond NIPS 2022
On the Adversarial Robustness of Mixture of Experts NIPS 2022
Sparse Non-Local CRF CVPR 2022
Fast and More Powerful Selective Inference for Sparse High-Order Interaction Model AAAI 2022
Sparse Mixers: Combining MoE and Mixing to build a more efficient BERT EMNLP 2022
The Optimal BERT Surgeon: Scalable and Accurate Second-Order Pruning for Large Language Models EMNLP 2022
Tricks for Training Sparse Translation Models NAACL 2022
Sparse Double Descent: Where Network Pruning Aggravates Overfitting ICML 2022
DeepSpeed-MoE: Advancing Mixture-of-Experts Inference and Training to Power Next-Generation AI Scale ICML 2022
Who Says Elephants Can’t Run: Bringing Large Scale MoE Models into Cloud Scale Production EMNLP 2022
Controlled Sparsity via Constrained Optimization or: How I Learned to Stop Tuning Penalties and Love Constraints NIPS 2022
Exploring the Whole Rashomon Set of Sparse Decision Trees NIPS 2022
EPIC TTS Models: Empirical Pruning Investigations Characterizing Text-To-Speech Models INTERSPEECH 2022
Differentially Private Model Compression NIPS 2022
Provable Benefits of Overparameterization in Model Compression: From Double Descent to Pruning Neural Networks AAAI 2021
Beyond Distillation: Task-level Mixture-of-Experts for Efficient Inference EMNLP 2021
Leveraging Sparse Linear Layers for Debuggable Deep Networks ICML 2021
BASE Layers: Simplifying Training of Large, Sparse Models ICML 2021