conftrace_
← Application Areas
Machine Learning › Application Areas ›

Efficient Computing

6,876 papers

Papers per year

Papers

Monarch: Expressive Structured Matrices for Efficient and Accurate Training ICML 2022
Variational Feature Pyramid Networks ICML 2022
Finding the Task-Optimal Low-Bit Sub-Distribution in Deep Neural Networks ICML 2022
GLaM: Efficient Scaling of Language Models with Mixture-of-Experts ICML 2022
Fast Relative Entropy Coding with A* coding ICML 2022
SPDY: Accurate Pruning with Speedup Guarantees ICML 2022
DepthShrinker: A New Compression Paradigm Towards Boosting Real-Hardware Efficiency of Compact Neural Networks ICML 2022
Fast and Reliable Evaluation of Adversarial Robustness with Minimum-Margin Attack ICML 2022
The State of Sparse Training in Deep Reinforcement Learning ICML 2022
NISPA: Neuro-Inspired Stability-Plasticity Adaptation for Continual Learning in Sparse Networks ICML 2022
HyperPrompt: Prompt-based Task-Conditioning of Transformers ICML 2022
DAdaQuant: Doubly-adaptive quantization for communication-efficient Federated Learning ICML 2022
A data-driven approach for learning to control computers ICML 2022
Flashlight: Enabling Innovation in Tools for Machine Learning ICML 2022
Dataset Condensation via Efficient Synthetic-Data Parameterization ICML 2022
Variational On-the-Fly Personalization ICML 2022
Exploiting Redundancy: Separable Group Convolutional Networks on Lie Groups ICML 2022
Spatial-Channel Token Distillation for Vision MLPs ICML 2022
TSPipe: Learn from Teacher Faster with Pipelines ICML 2022
Gating Dropout: Communication-efficient Regularization for Sparsely Activated Transformers ICML 2022
GACT: Activation Compressed Training for Generic Network Architectures ICML 2022
Prioritized Training on Points that are Learnable, Worth Learning, and not yet Learnt ICML 2022
Proximal and Federated Random Reshuffling ICML 2022
AutoSNN: Towards Energy-Efficient Spiking Neural Networks ICML 2022
Overcoming Oscillations in Quantization-Aware Training ICML 2022