Establishes non-asymptotic Gaussian approximation bounds for federated LSA with explicit communication-heterogeneity trade-offs and introduces an online multiplier bootstrap for last-iterate inference with validity guarantees.
hub
International conference on machine learning , pages=
21 Pith papers cite this work. Polarity classification is still indexing.
21
Pith papers citing it
hub tools
citation-role summary
method 2
citation-polarity summary
roles
method 2polarities
use method 2representative citing papers
DRATS derives a minimax objective from a feasibility formulation of MTRL to adaptively sample tasks with the largest return gaps, leading to better worst-task performance on MetaWorld benchmarks.
HPO enables unbiased policy optimization in hybrid action spaces by mixing differentiable simulation gradients with score-function estimates, outperforming PPO as continuous dimensions increase.
Introduces TBPO, which derives a Bregman-divergence density-ratio matching objective for token-level preference optimization that generalizes DPO while preserving the induced optimal policy.
Synthetic data augmentation helps channel-mixing time series models but degrades channel-independent ones, with reliable gains only from seasonal-trend generators and gradual schedules in low-resource settings.
LeGS turns density control in 3D Gaussian Splatting into a learnable RL policy whose reward is derived from a closed-form sensitivity analysis that measures each Gaussian's marginal contribution to reconstruction quality.
Scion is a new stochastic LMO-based optimizer family that unifies existing methods, supports unconstrained problems, and delivers hyperparameter transferability plus speedups on nanoGPT training.
DRIFT enables stable offline-to-online fine-tuning of CTMC policies in discrete RL via advantage-weighted discrete flow matching, path-space regularization, and candidate-set approximation.
HölderPO unifies token-level aggregation in GRPO via the Hölder mean with a tunable p parameter and annealing schedule, delivering 54.9% average accuracy on math benchmarks and 93.8% success on ALFWorld.
dFlowGRPO is a new rate-aware RL method for discrete flow models that outperforms prior GRPO approaches on image generation and matches continuous flow models while supporting broad probability paths.
MARS replaces additive clipping and soft penalties in multi-agent trust-region methods with a symmetric geometric barrier, matching or exceeding MAPPO and MASPO performance across 47 tasks in eight environments.
Response times modeled as drift-diffusion processes enable consistent estimation of population-average preferences from heterogeneous anonymous binary choices.
OGPO enables sample-efficient full-finetuning of generative control policies via off-policy critics and modified PPO, achieving SOTA on robot manipulation tasks while rescuing poorly initialized behavior cloning policies without expert data.
A new adaptive variance estimator for relative sparsity coefficients is introduced that fully utilizes the prior asymptotic normality theorem and incorporates variable selection effects.
TeamTR is a trust-region framework for multi-agent LLM fine-tuning that resamples trajectories after each update to convert quadratic compounding occupancy shift into linear scaling and yields per-update improvement lower bounds.
Unsupervised behavioral mode discovery combined with mutual information rewards enables RL fine-tuning of multimodal generative policies that achieves higher success rates without losing action diversity.
APMPO boosts average Pass@1 scores on math reasoning benchmarks by 3 points over GRPO by using an adaptive power-mean policy objective and feedback-driven clipping bounds in RLVR training.
The note claims linear convergence of WPO in entropy-regularized MDPs by combining mean-field gradient flow analysis with a local log-Sobolev inequality under a regularity assumption.
Offline model-based RL policy trained solely on DIII-D historical data is deployed on the tokamak and yields promising real-world rotation profile control.
The study applies transfer learning to deep RL in OpenAI car racing, observing that model-based approaches outperform model-free methods and that transfer boosts target domain performance.
citing papers explorer
-
Gaussian Approximation and Multiplier Bootstrap for Federated Linear Stochastic Approximation
Establishes non-asymptotic Gaussian approximation bounds for federated LSA with explicit communication-heterogeneity trade-offs and introduces an online multiplier bootstrap for last-iterate inference with validity guarantees.
-
Distributionally Robust Multi-Task Reinforcement Learning via Adaptive Task Sampling
DRATS derives a minimax objective from a feasibility formulation of MTRL to adaptively sample tasks with the largest return gaps, leading to better worst-task performance on MetaWorld benchmarks.
-
Policy Optimization in Hybrid Discrete-Continuous Action Spaces via Mixed Gradients
HPO enables unbiased policy optimization in hybrid action spaces by mixing differentiable simulation gradients with score-function estimates, outperforming PPO as continuous dimensions increase.
-
TokenRatio: Principled Token-Level Preference Optimization via Ratio Matching
Introduces TBPO, which derives a Bregman-divergence density-ratio matching objective for token-level preference optimization that generalizes DPO while preserving the induced optimal policy.
-
Does Synthetic Data Help? Empirical Evidence from Deep Learning Time Series Forecasters
Synthetic data augmentation helps channel-mixing time series models but degrades channel-independent ones, with reliable gains only from seasonal-trend generators and gradual schedules in low-resource settings.
-
Beyond Heuristics: Learnable Density Control for 3D Gaussian Splatting
LeGS turns density control in 3D Gaussian Splatting into a learnable RL policy whose reward is derived from a closed-form sensitivity analysis that measures each Gaussian's marginal contribution to reconstruction quality.
-
Training Deep Learning Models with Norm-Constrained LMOs
Scion is a new stochastic LMO-based optimizer family that unifies existing methods, supports unconstrained problems, and delivers hyperparameter transferability plus speedups on nanoGPT training.
-
Discrete Flow Matching for Offline-to-Online Reinforcement Learning
DRIFT enables stable offline-to-online fine-tuning of CTMC policies in discrete RL via advantage-weighted discrete flow matching, path-space regularization, and candidate-set approximation.
-
Holder Policy Optimisation
HölderPO unifies token-level aggregation in GRPO via the Hölder mean with a tunable p parameter and annealing schedule, delivering 54.9% average accuracy on math benchmarks and 93.8% success on ALFWorld.
-
dFlowGRPO: Rate-Aware Policy Optimization for Discrete Flow Models
dFlowGRPO is a new rate-aware RL method for discrete flow models that outperforms prior GRPO approaches on image generation and matches continuous flow models while supporting broad probability paths.
-
Rethinking Ratio-Based Trust Regions for Policy Optimization in Multi-Agent Reinforcement Learning
MARS replaces additive clipping and soft penalties in multi-agent trust-region methods with a symmetric geometric barrier, matching or exceeding MAPPO and MASPO performance across 47 tasks in eight environments.
-
Response Time Enhances Alignment with Heterogeneous Preferences
Response times modeled as drift-diffusion processes enable consistent estimation of population-average preferences from heterogeneous anonymous binary choices.
-
OGPO: Sample Efficient Full-Finetuning of Generative Control Policies
OGPO enables sample-efficient full-finetuning of generative control policies via off-policy critics and modified PPO, achieving SOTA on robot manipulation tasks while rescuing poorly initialized behavior cloning policies without expert data.
-
An adaptive variance estimator for relative sparsity
A new adaptive variance estimator for relative sparsity coefficients is introduced that fully utilizes the prior asymptotic normality theorem and incorporates variable selection effects.
-
TeamTR: Trust-Region Fine-Tuning for Multi-Agent LLM Coordination
TeamTR is a trust-region framework for multi-agent LLM fine-tuning that resamples trajectories after each update to convert quadratic compounding occupancy shift into linear scaling and yields per-update improvement lower bounds.
-
Behavioral Mode Discovery for Fine-tuning Multimodal Generative Policies
Unsupervised behavioral mode discovery combined with mutual information rewards enables RL fine-tuning of multimodal generative policies that achieves higher success rates without losing action diversity.
-
Adapt to Thrive! Adaptive Power-Mean Policy Optimization for Improved LLM Reasoning
APMPO boosts average Pass@1 scores on math reasoning benchmarks by 3 points over GRPO by using an adaptive power-mean policy objective and feedback-driven clipping bounds in RLVR training.
-
A note on convergence of Wasserstein policy optimization
The note claims linear convergence of WPO in entropy-regularized MDPs by combining mean-field gradient flow analysis with a local log-Sobolev inequality under a regularity assumption.
-
Offline Reinforcement Learning for Rotation Profile Control in Tokamaks
Offline model-based RL policy trained solely on DIII-D historical data is deployed on the tokamak and yields promising real-world rotation profile control.
-
Transfer Learning for Customized Car Racing Environments
The study applies transfer learning to deep RL in OpenAI car racing, observing that model-based approaches outperform model-free methods and that transfer boosts target domain performance.
- Trust Region Inverse Reinforcement Learning: Explicit Dual Ascent using Local Policy Updates