Local LMO is a new projection-free method that achieves the convergence rates of projected gradient descent for constrained optimization by using local linear minimization oracles over small balls.
Efficient projections onto the l1-ball for learning in high dimensions
8 Pith papers cite this work. Polarity classification is still indexing.
8
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
Extends variable projection to constrained separable nonlinear least-squares via bilevel collapse, yielding exact reduced gradients and a convergent conditional-gradient algorithm.
The paper presents stable-worldmodel (swm), a platform with high-performance data layer, modern world model baselines, planning solvers, and extended environments for reproducible research and generalization evaluation.
Sticky factorial HDP-HMMs applied to multimodal valence-arousal trajectories identify interpretable persistent emotional regimes in conversations, outperforming Gaussian HMM baselines in consistency metrics and enabling context-augmented LLM responses.
A feedback-based dynamic pricing framework reduces peak demand and load variation in simulated distribution networks with hundreds of automated home energy management systems controlling HVAC, batteries, and flexible loads.
Randomized SINDy is a probabilistic sequential learning algorithm for dynamic data that claims a rigorous PAC learning guarantee via functional analysis and shows results on regression and binary classification tasks.
citing papers explorer
-
Local LMO: Constrained Gradient Optimization via a Local Linear Minimization Oracle
Local LMO is a new projection-free method that achieves the convergence rates of projected gradient descent for constrained optimization by using local linear minimization oracles over small balls.
-
Constrained Variable Projection for Structured Problems
Extends variable projection to constrained separable nonlinear least-squares via bilevel collapse, yielding exact reduced gradients and a convergent conditional-gradient algorithm.
-
stable-worldmodel: A Platform for Reproducible World Modeling Research and Evaluation
The paper presents stable-worldmodel (swm), a platform with high-performance data layer, modern world model baselines, planning solvers, and extended environments for reproducible research and generalization evaluation.
-
Multimodal Hidden Markov Models for Persistent Emotional State Tracking
Sticky factorial HDP-HMMs applied to multimodal valence-arousal trajectories identify interpretable persistent emotional regimes in conversations, outperforming Gaussian HMM baselines in consistency metrics and enabling context-augmented LLM responses.
-
Unlocking Deep Demand Flexibility via Dynamic Signals
A feedback-based dynamic pricing framework reduces peak demand and load variation in simulated distribution networks with hundreds of automated home energy management systems controlling HVAC, batteries, and flexible loads.
-
Sequential Regression Learning with Randomized Algorithms
Randomized SINDy is a probabilistic sequential learning algorithm for dynamic data that claims a rigorous PAC learning guarantee via functional analysis and shows results on regression and binary classification tasks.
- REALISTA: Realistic Latent Adversarial Attacks that Elicit LLM Hallucinations
- RouterWise: Joint Resource Allocation and Routing for Latency-Aware Multi-Model LLM Serving