← Optimization & Theory
Deep Learning › Optimization & Theory ›

Optimization

1638 directly classified papers

Papers per year

Papers

VPTQ: Extreme Low-bit Vector Post-Training Quantization for Large Language Models EMNLP 2024
Searching for Efficient Linear Layers over a Continuous Space of Structured Matrices NIPS 2024
AdjointDEIS: Efficient Gradients for Diffusion Models NIPS 2024
Extending Context Window of Large Language Models from a Distributional Perspective EMNLP 2024
General Tail Bounds for Non-Smooth Stochastic Mirror Descent AISTATS 2024
KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization NIPS 2024
Learning from Teaching Regularization: Generalizable Correlations Should be Easy to Imitate NIPS 2024
Optimized Speculative Sampling for GPU Hardware Accelerators EMNLP 2024
MicroAdam: Accurate Adaptive Optimization with Low Space Overhead and Provable Convergence NIPS 2024
SOUL: Unlocking the Power of Second-Order Optimization for LLM Unlearning EMNLP 2024
Input-to-State Stable Coupled Oscillator Networks for Closed-form Model-based Control in Latent Space NIPS 2024
Rethinking Pruning Large Language Models: Benefits and Pitfalls of Reconstruction Error Minimization EMNLP 2024
Practical Shuffle Coding NIPS 2024
AdaZeta: Adaptive Zeroth-Order Tensor-Train Adaption for Memory-Efficient Large Language Models Fine-Tuning EMNLP 2024
GACL: Exemplar-Free Generalized Analytic Continual Learning NIPS 2024
Countering the Communication Bottleneck in Federated Learning: A Highly Efficient Zero-Order Optimization Technique JMLR 2024
Bridging the Divide: Reconsidering Softmax and Linear Attention NIPS 2024
Revive Re-weighting in Imbalanced Learning by Density Ratio Estimation NIPS 2024
Confidence Calibration of Classifiers with Many Classes NIPS 2024
Graph-enhanced Optimizers for Structure-aware Recommendation Embedding Evolution NIPS 2024
Orchid: Flexible and Data-Dependent Convolution for Sequence Modeling NIPS 2024
CoMERA: Computing- and Memory-Efficient Training via Rank-Adaptive Tensor Optimization NIPS 2024
BPQP: A Differentiable Convex Optimization Framework for Efficient End-to-End Learning NIPS 2024
Towards Dynamic Message Passing on Graphs NIPS 2024
Accelerating Relative Entropy Coding with Space Partitioning NIPS 2024