Efficient Alternating Minimization with Applications to Weighted Low Rank Approximation
cs.LG, math.OC
Submitted: 2023-06-07
Updated: 2026-11-11
Terminology
Sources
- Federated Empirical Risk Minimization via Second-Order Method
- RoPE Attention Can Be Trained in Almost Linear Time
- Attention Scheme Inspired Softmax Regression
- Discrepancy Minimization in Input-Sparsity Time
- Faster Robust Tensor Power Method for Arbitrary Order
- A Faster Small Treewidth SDP Solver
- A Fast Optimization View: Reformulating Single Layer Attention in LLM Based on Tensor and SVM Trick, and Solving It in Matrix Multiplication Time
- GradientCoin: A Peer-to-Peer Decentralized Large Language Models
- Language model compression with weighted low-rank factorization
- On Differentially Private String Distances
- Conv-Basis: A New Paradigm for Efficient Attention Inference and Gradient Computation in Transformers
- A Faster $k$-means++ Algorithm
- Local Convergence of Approximate Newton Method for Two Layer Nonlinear Regression
- Inverting the Leverage Score Gradient: An Efficient Approximate Newton Method
- Solving Regularized Exp, Cosh and Sinh Regression Problems
- Sublinear Least-Squares Value Iteration via Locality Sensitive Hashing
- A Mathematical Abstraction for Balancing the Trade-off Between Creativity and Reality in Large Language Models
- A Unified Scheme of ResNet and Softmax
- Accelerating Frank-Wolfe Algorithm using Low-Dimensional and Adaptive Data Structures
- Speeding Up Sparsification using Inner Product Search Data Structures
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis