Optimization

Beyond Efficiency: Molecular Data Pruning for Enhanced Generalization NeurIPS 2024 Beyond Implicit Bias: The Insignificance of SGD Noise in Online Learning ICML 2024 Beyond One-Preference-Fits-All Alignment: Multi-Objective Direct Preference Optimization ACL 2024 Beyond Primal-Dual Methods in Bandits with Stochastic and Adversarial Constraints NeurIPS 2024 Beyond Reverse KL: Generalizing Direct Preference Optimization with Diverse Divergence Constraints ICLR 2024 Beyond Single Stationary Policies: Meta-Task Players as Naturally Superior Collaborators NeurIPS 2024 Beyond Stationarity: Convergence Analysis of Stochastic Softmax Policy Gradient Methods ICLR 2024 Beyond the Federation: Topology-aware Federated Learning for Generalization to Unseen Clients ICML 2024 Biased Temporal Convolution Graph Network for Time Series Forecasting with Missing Values ICLR 2024 Bias in Motion: Theoretical Insights into the Dynamics of Bias in SGD Training NeurIPS 2024 Big Learning Expectation Maximization AAAI 2024 Bilevel Optimization under Unbounded Smoothness: A New Algorithm and Convergence Analysis ICLR 2024 BilevelPruning: Unified Dynamic and Static Channel Pruning for Convolutional Neural Networks CVPR 2024 Binary Decomposition: A Problem Transformation Perspective for Open-Set Semi-Supervised Learning ICML 2024 BIPEFT: Budget-Guided Iterative Search for Parameter Efficient Fine-Tuning of Large Pretrained Language Models EMNLP 2024 BiPer: Binary Neural Networks using a Periodic Function CVPR 2024 Birdie: Advancing State Space Language Modeling with Dynamic Mixtures of Training Objectives EMNLP 2024 BiSHop: Bi-Directional Cellular Learning for Tabular Data with Generalized Sparse Modern Hopfield Model ICML 2024 Bisimulation Metrics are Optimal Transport Distances, and Can be Computed Efficiently NeurIPS 2024 BitDistiller: Unleashing the Potential of Sub-4-Bit LLMs via Self-Distillation ACL 2024 Blind Image Restoration via Fast Diffusion Inversion NeurIPS 2024 Block Acceleration Without Momentum: On Optimal Stepsizes of Block Gradient Descent for Least-Squares ICML 2024 Block-Level Goal Recognition Design AAAI 2024 BLO-SAM: Bi-level Optimization Based Finetuning of the Segment Anything Model for Overfitting-Preventing Semantic Segmentation ICML 2024 BOBA: Byzantine-Robust Federated Learning with Label Skewness AISTATS 2024