Neural Network Optimization

Tight Risk Bounds for Gradient Descent on Separable Data NeurIPS 2023 Time-Reversed Dissipation Induces Duality Between Minimizing Gradient Norm and Function Value NeurIPS 2023 TLM: Token-Level Masking for Transformers EMNLP 2023 TokenDrop + BucketSampler: Towards Efficient Padding-free Fine-tuning of Language Models EMNLP 2023 TorchOpt: An Efficient Library for Differentiable Optimization JMLR 2023 TORE: Token Reduction for Efficient Human Mesh Recovery with Transformer ICCV 2023 To Stay or Not to Stay in the Pre-train Basin: Insights on Ensembling in Transfer Learning NeurIPS 2023 Toward Edge-Efficient Dense Predictions With Synergistic Multi-Task Neural Architecture Search WACV 2023 Towards Bridging the Performance Gaps of Joint Energy-Based Models CVPR 2023 Towards Constituting Mathematical Structures for Learning to Optimize ICML 2023 Towards Data-Agnostic Pruning At Initialization: What Makes a Good Sparse Mask? NeurIPS 2023 Towards Deep Attention in Graph Neural Networks: Problems and Remedies ICML 2023 Towards Memory- and Time-Efficient Backpropagation for Training Spiking Neural Networks ICCV 2023 Towards More Efficient Insertion Transformer with Fractional Positional Encoding EACL 2023 Trainability, Expressivity and Interpretability in Gated Neural ODEs ICML 2023 Trainable Weight Averaging: Efficient Training by Optimizing Historical Solutions ICLR 2023 Trained MT Metrics Learn to Cope with Machine-translated References EMNLP 2023 Train Faster, Perform Better: Modular Adaptive Training in Over-Parameterized Models NeurIPS 2023 Training biologically plausible recurrent neural networks on cognitive tasks with long-term dependencies NeurIPS 2023 Training Deep Surrogate Models with Large Scale Online Learning ICML 2023 Training shallow ReLU networks on noisy data using hinge loss: when do we overfit and is it benign? NeurIPS 2023 Trajectory Alignment: Understanding the Edge of Stability Phenomenon via Bifurcation Theory NeurIPS 2023 Trajectory Unified Transformer for Pedestrian Trajectory Prediction ICCV 2023 Transfer Learning Enhanced DeepONet for Long-Time Prediction of Evolution Equations AAAI 2023 Transformer-based Hebrew NLP models for Short Answer Scoring in Biology ACL 2023