The Stability of Online Algorithms
No mentions found
This entity hasn't been tracked yet, or Iris is still building its knowledge base.
Related Articles from SNS
The Stability of Online Algorithms in Performative Prediction
Announce Type: replace Abstract: The use of algorithmic predictions in decision-making leads to a feedback loop where the models we deploy actively influence the data distributions we see, and later use to retrain on. This dynamic was formalized by Perdomo et al. 2020 in their work on performative prediction. Our main result is an unconditional reduction showing that any no-regret algorithm deployed in performative settings converges to a (mixed) performatively stable equilibrium: a solution...
Reinforcement Learning for Flow-Matching Policies with Density Transport
Announce Type: new Abstract: We present an online reinforcement learning (RL) algorithm for fine-tuning flow-matching policies in continuous-control problems. Our key insight is to view RL-based policy improvement as a transport of action densities towards regions of high reward, which naturally aligns with the transport formulation of flow matching models. Prior methods either approximate the current or optimal policy distribution or resort to distillation, which introduces biased gradients...
Estimating Bidirectional Causal Effects with Large Scale Online Kernel Learning
Announce Type: replace-cross Abstract: In this study, a scalable online kernel learning framework is proposed for estimating bidirectional causal effects in systems characterized by mutual dependence and heteroskedasticity. Traditional causal inference often focuses on unidirectional effects, overlooking the common bidirectional relationships in real-world phenomena. Building on heteroskedasticity-based identification, the proposed method integrates a quasi-maximum likelihood estimator for...
FM-IRL: Flow-Matching for Reward Modeling and Policy Regularization in Reinforcement Learning
arXiv:2510.09222v3 Announce Type: replace Abstract: Flow Matching (FM) has shown remarkable ability in modeling complex distributions and achieves strong performance in offline imitation learning for cloning expert behaviors. However, despite its behavioral cloning expressiveness, FM-based policies are inherently limited by their lack of environmental interaction and exploration. This leads to poor generalization in unseen scenarios beyond the expert demonstrations, underscoring the...
Train at Moving Edge: Online-Verified Prompt Selection for Efficient RL Training of Large Reasoning Model
Announce Type: replace Abstract: Reinforcement learning (RL) has become essential for post-training large language models (LLMs) in reasoning tasks. While scaling rollouts can stabilize training and enhance performance, the computational overhead is a critical issue. In algorithms like GRPO, multiple rollouts per prompt incur prohibitive costs, as a large portion of prompts provide negligible gradients and are thus of low utility.
Crazyflow: An Accurate, GPU-Accelerated, Differentiable Drone Simulator in JAX
arXiv:2606.01478v2 Announce Type: replace Abstract: High-quality, large-scale synthetic data from simulations is becoming a cornerstone for pushing the capabilities of robot algorithms. While aerial robotics simulators have evolved to support specialized needs such as fidelity, differentiability, and swarms independently, a unified platform that can synthesize data across all these domains is missing. In this work, we propose Crazyflow, a simulator designed to push the limits of...
Crazyflow: An Accurate, GPU-Accelerated, Differentiable Drone Simulator in JAX
Announce Type: new Abstract: High-quality, large-scale synthetic data from simulations is becoming a cornerstone for pushing the capabilities of robot algorithms. While aerial robotics simulators have evolved to support specialized needs such as fidelity, differentiability, and swarms independently, a unified platform that can synthesize data across all these domains is missing. In this work, we propose Crazyflow, a simulator designed to push the limits of aerial-robotics algorithm...
AdaGRPO: A Capability-Aware Adaptive Enhancement for Flow-based GRPO
Announce Type: new Abstract: Group Relative Policy Optimization (GRPO) has demonstrated remarkable success in aligning text-to-image (T2I) flow models with human preferences. However, we have identified that the learning loop of current flow-based GRPO is fundamentally decoupled from the learner's current capability, suffering from critical blind spots at both prompt selection and advantage estimation: (i) Existing methods sample prompts randomly, overlooking the substantial impact of data...
Online Learning for Supervisory Switching Control
arXiv:2603.14762v3 Announce Type: replace-cross Abstract: We study supervisory switching control for partially-observed linear dynamical systems. The objective is to identify and deploy a suitable controller for the unknown system by periodically selecting among a collection of $N$ candidate controllers, some of which may destabilize the underlying system. While classical estimator-based supervisory control guarantees asymptotic stability, it lacks quantitative finite-time performance bounds.
Learning to Bid in FCR Markets: A Best-of-Both-Worlds Approach
Announce Type: new Abstract: Bidding in the European Frequency Containment Reserve (FCR) market is challenging for flexibility providers because competing offers are hidden and bidders observe only partial feedback form the market, such as, clearing price and awarded quantity. For a participant active in a single country, we show that the multi-country FCR clearing problem can be recast as a repeated multi-unit uniform-price auction against an endogenous vector of opposing bids. This...