Alec Koppel

Orcid: 0000-0003-2447-2873

According to our database1, Alec Koppel authored at least 132 papers between 2015 and 2024.

Collaborative distances:
  • Dijkstra number2 of four.
  • Erdős number3 of four.

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

Online presence:

On csauthors.net:

Bibliography

2024
Online MCMC Thinning with Kernelized Stein Discrepancy.
SIAM J. Math. Data Sci., March, 2024

Occupancy Information Ratio: Infinite-Horizon, Information-Directed, Parameterized Policy Search.
SIAM J. Control. Optim., 2024

On the Sample Complexity and Metastability of Heavy-tailed Policy Search in Continuous Control.
J. Mach. Learn. Res., 2024

GenARM: Reward Guided Generation with Autoregressive Reward Model for Test-time Alignment.
CoRR, 2024

Partially Observable Contextual Bandits with Linear Payoffs.
CoRR, 2024

SAIL: Self-Improving Efficient Online Alignment of Large Language Models.
CoRR, 2024

Robust Cooperative Multi-Agent Reinforcement Learning:A Mean-Field Type Game Perspective.
CoRR, 2024

Compressed Online Learning of Conditional Mean Embedding.
CoRR, 2024

Global Optimality without Mixing Time Oracles in Average-reward RL via Multi-level Actor-Critic.
CoRR, 2024

Independent RL for Cooperative-Competitive Agents: A Mean-Field Perspective.
CoRR, 2024

Beyond Joint Demonstrations: Personalized Expert Guidance for Efficient Multi-Agent Reinforcement Learning.
CoRR, 2024

MaxMin-RLHF: Towards Equitable Alignment of Large Language Models with Diverse Human Preferences.
CoRR, 2024

Robust cooperative multi-agent reinforcement learning: A mean-field type game perspective.
Proceedings of the 6th Annual Learning for Dynamics & Control Conference, 2024

Towards Global Optimality for Practical Average Reward Reinforcement Learning without Mixing Time Oracles.
Proceedings of the Forty-first International Conference on Machine Learning, 2024

Information-Directed Pessimism for Offline Reinforcement Learning.
Proceedings of the Forty-first International Conference on Machine Learning, 2024

MaxMin-RLHF: Alignment with Diverse Human Preferences.
Proceedings of the Forty-first International Conference on Machine Learning, 2024

Efficient Inverse Multiagent Learning.
Proceedings of the Twelfth International Conference on Learning Representations, 2024

PARL: A Unified Framework for Policy Alignment in Reinforcement Learning from Human Feedback.
Proceedings of the Twelfth International Conference on Learning Representations, 2024

Sharpened Lazy Incremental Quasi-Newton Method.
Proceedings of the International Conference on Artificial Intelligence and Statistics, 2024

2023
On the sample complexity of actor-critic method for reinforcement learning with function approximation.
Mach. Learn., July, 2023

Near-Optimal Fair Resource Allocation for Strategic Agents without Money: A Data-Driven Approach.
CoRR, 2023

Byzantine-Resilient Decentralized Multi-Armed Bandits.
CoRR, 2023

Aligning Agent Policy with Externalities: Reward Design via Bilevel RL.
CoRR, 2023

Limited-Memory Greedy Quasi-Newton Method with Non-asymptotic Superlinear Convergence Rate.
CoRR, 2023

Ada-NAV: Adaptive Trajectory-Based Sample Efficient Policy Learning for Robotic Navigation.
CoRR, 2023

A Gradient-based Approach for Online Robust Deep Neural Network Training with Noisy Labels.
CoRR, 2023

Scalable Primal-Dual Actor-Critic Method for Safe Multi-Agent RL with General Utilities.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Decentralized Multi-agent Exploration with Limited Inter-agent Communications.
Proceedings of the IEEE International Conference on Robotics and Automation, 2023

Dealing with Sparse Rewards in Continuous Control Robotics via Heavy-Tailed Policy Optimization.
Proceedings of the IEEE International Conference on Robotics and Automation, 2023

Beyond Exponentially Fast Mixing in Average-Reward Reinforcement Learning via Multi-Level Monte Carlo Actor-Critic.
Proceedings of the International Conference on Machine Learning, 2023

STEERING : Stein Information Directed Exploration for Model-Based Reinforcement Learning.
Proceedings of the International Conference on Machine Learning, 2023

Information-Directed Policy Search in Sparse-Reward Settings via the Occupancy Information Ratio.
Proceedings of the 57th Annual Conference on Information Sciences and Systems, 2023

Bi-Level Nonstationary Kernels for Online Gaussian Process Regression.
Proceedings of the 19th IEEE International Conference on Automation Science and Engineering, 2023

Scalable Multi-Agent Reinforcement Learning with General Utilities.
Proceedings of the American Control Conference, 2023

Oracle-free Reinforcement Learning in Mean-Field Games along a Single Sample Path.
Proceedings of the International Conference on Artificial Intelligence and Statistics, 2023

Posterior Coreset Construction with Kernelized Stein Discrepancy for Model-Based Reinforcement Learning.
Proceedings of the Thirty-Seventh AAAI Conference on Artificial Intelligence, 2023

2022
Balancing Rates and Variance via Adaptive Batch-Size for Stochastic Optimization Problems.
IEEE Trans. Signal Process., 2022

Sparse Representations of Positive Functions via First- and Second-Order Pseudo-Mirror Descent.
IEEE Trans. Signal Process., 2022

Escaping Saddle Points for Successive Convex Approximation.
IEEE Trans. Signal Process., 2022

Dense Incremental Metric-Semantic Mapping for Multiagent Systems via Sparse Gaussian Process Regression.
IEEE Trans. Robotics, 2022

Collaborative one-shot beamforming under localization errors: A discrete optimization approach.
Signal Process., 2022

FedBC: Calibrating Global and Local Models via Federated Learning Beyond Consensus.
CoRR, 2022

Dealing with Sparse Rewards in Continuous Control Robotics via Heavy-Tailed Policies.
CoRR, 2022

Online, Informative MCMC Thinning with Kernelized Stein Discrepancy.
CoRR, 2022

Distributed Riemannian Optimization with Lazy Communication for Collaborative Geometric Estimation.
Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems, 2022

Sharpened Quasi-Newton Methods: Faster Superlinear Rate and Larger Local Convergence Neighborhood.
Proceedings of the International Conference on Machine Learning, 2022

On the Hidden Biases of Policy Mirror Ascent in Continuous Action Spaces.
Proceedings of the International Conference on Machine Learning, 2022

On Submodular Set Cover Problems for Near-Optimal Online Kernel Basis Selection.
Proceedings of the IEEE International Conference on Acoustics, 2022

Policy Gradient for Ratio Optimization: A Case Study.
Proceedings of the 56th Annual Conference on Information Sciences and Systems, 2022

Convergence Rates of Average-Reward Multi-agent Reinforcement Learning via Randomized Linear Programming.
Proceedings of the 61st IEEE Conference on Decision and Control, 2022

Distributed Gaussian Process Mapping for Robot Teams with Time-varying Communication.
Proceedings of the American Control Conference, 2022

Multi-Agent Reinforcement Learning with General Utilities via Decentralized Shadow Reward Actor-Critic.
Proceedings of the Thirty-Sixth AAAI Conference on Artificial Intelligence, 2022

Achieving Zero Constraint Violation for Constrained Reinforcement Learning via Primal-Dual Approach.
Proceedings of the Thirty-Sixth AAAI Conference on Artificial Intelligence, 2022

2021
Nearly Consistent Finite Particle Estimates in Streaming Importance Sampling.
IEEE Trans. Signal Process., 2021

Dynamic Online Learning via Frank-Wolfe Algorithm.
IEEE Trans. Signal Process., 2021

Nonparametric Compositional Stochastic Optimization for Risk-Sensitive Kernel Learning.
IEEE Trans. Signal Process., 2021

Adaptive Kernel Learning in Heterogeneous Networks.
IEEE Trans. Signal Inf. Process. over Networks, 2021

Policy Evaluation in Continuous MDPs With Efficient Kernelized Gradient Temporal Difference.
IEEE Trans. Autom. Control., 2021

Consistent online Gaussian process regression without the sample complexity bottleneck.
Stat. Comput., 2021

Cautious Reinforcement Learning via Distributional Risk in the Dual Domain.
IEEE J. Sel. Areas Inf. Theory, 2021

MARL with General Utilities via Decentralized Shadow Reward Actor-Critic.
CoRR, 2021

Dense Incremental Metric-Semantic Mapping for Multi-Agent Systems via Sparse Gaussian Process Regression.
CoRR, 2021

Wasserstein-Splitting Gaussian Process Regression for Heterogeneous Online Bayesian Inference.
Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems, 2021

A Dynamical Systems Perspective on Online Bayesian Nonparametric Estimators with Adaptive Hyperparameters.
Proceedings of the IEEE International Conference on Acoustics, 2021

Semiparametric Information State Embedding for Policy Search under Imperfect Information.
Proceedings of the 2021 60th IEEE Conference on Decision and Control (CDC), 2021

Intermittent Communications in Decentralized Shadow Reward Actor-Critic.
Proceedings of the 2021 60th IEEE Conference on Decision and Control (CDC), 2021

Beyond Cumulative Returns via Reinforcement Learning over State-Action Occupancy Measures.
Proceedings of the 2021 American Control Conference, 2021

Joint Position and Beamforming Control via Alternating Nonlinear Least-Squares with a Hierarchical Gamma Prior.
Proceedings of the 2021 American Control Conference, 2021

Collaborative Beamforming for Agents with Localization Errors.
Proceedings of the 55th Asilomar Conference on Signals, Systems, and Computers, 2021

Randomized Linear Programming for Tabular Average-Cost Multi-agent Reinforcement Learning.
Proceedings of the 55th Asilomar Conference on Signals, Systems, and Computers, 2021

Projected Pseudo-Mirror Descent in Reproducing Kernel Hilbert Space.
Proceedings of the 55th Asilomar Conference on Signals, Systems, and Computers, 2021

2020
High-Dimensional Nonconvex Stochastic Optimization by Doubly Stochastic Successive Convex Approximation.
IEEE Trans. Signal Process., 2020

Optimally Compressed Nonparametric Online Learning: Tradeoffs between memory and consistency.
IEEE Signal Process. Mag., 2020

Global Convergence of Policy Gradient Methods to (Almost) Locally Optimal Policies.
SIAM J. Control. Optim., 2020

Asynchronous and Parallel Distributed Pose Graph Optimization.
IEEE Robotics Autom. Lett., 2020

A Class of Parallel Doubly Stochastic Algorithms for Large-Scale Learning.
J. Mach. Learn. Res., 2020

Sparse Representations of Positive Functions via Projected Pseudo-Mirror Descent.
CoRR, 2020

A Markov Decision Process Approach to Active Meta Learning.
CoRR, 2020

Distributed Beamforming for Agents with Localization Errors.
CoRR, 2020

Efficient Gaussian Process Bandits by Believing only Informative Actions.
CoRR, 2020

Variational Policy Gradient Method for Reinforcement Learning with General Utilities.
Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Efficient Large-Scale Gaussian Process Bandits by Believing only Informative Actions.
Proceedings of the 2nd Annual Conference on Learning for Dynamics and Control, 2020

Dense Incremental Metric-Semantic Mapping via Sparse Gaussian Process Regression.
Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems, 2020

Projection Free Dynamic Online Learning.
Proceedings of the 2020 IEEE International Conference on Acoustics, 2020

Balancing Rates and Variance via Adaptive Batch-Sizes in First-Order Stochastic Optimization.
Proceedings of the 2020 IEEE International Conference on Acoustics, 2020

Reduced-rank Least Squares Parameter Estimation in the Presence of Byzantine Sensors.
Proceedings of the 54th Annual Conference on Information Sciences and Systems, 2020

Trading Dynamic Regret for Model Complexity in Nonstationary Nonparametric Optimization.
Proceedings of the 2020 American Control Conference, 2020

Conservative Multi-agent Online Kernel Learning in Heterogeneous Networks.
Proceedings of the 54th Asilomar Conference on Signals, Systems, and Computers, 2020

2019
Projected Stochastic Primal-Dual Method for Constrained Online Learning With Kernels.
IEEE Trans. Signal Process., 2019

Asynchronous Saddle Point Algorithm for Stochastic Optimization in Heterogeneous Networks.
IEEE Trans. Signal Process., 2019

Asynchronous Online Learning in Multi-Agent Systems With Proximity Constraints.
IEEE Trans. Signal Inf. Process. over Networks, 2019

Parsimonious Online Learning with Kernels via Sparse Projections in Function Space.
J. Mach. Learn. Res., 2019

Optimally Compressed Nonparametric Online Learning.
CoRR, 2019

Approximate Shannon Sampling in Importance Sampling: Nearly Consistent Finite Particle Estimates.
CoRR, 2019

Nonstationary Nonparametric Online Learning: Balancing Dynamic Regret and Model Parsimony.
CoRR, 2019

Policy Search in Infinite-Horizon Discounted Reinforcement Learning: Advances through Connections to Non-Convex Optimization : Invited Presentation.
Proceedings of the 53rd Annual Conference on Information Sciences and Systems, 2019

Convergence and Iteration Complexity of Policy Gradient Method for Infinite-horizon Reinforcement Learning.
Proceedings of the 58th IEEE Conference on Decision and Control, 2019

Distributed Online Learning over Time-varying Graphs via Proximal Gradient Descent.
Proceedings of the 58th IEEE Conference on Decision and Control, 2019

Policy Gradient using Weak Derivatives for Reinforcement Learning.
Proceedings of the 58th IEEE Conference on Decision and Control, 2019

Controlling the Bias-Variance Tradeoff via Coherent Risk for Robust Learning with Kernels.
Proceedings of the 2019 American Control Conference, 2019

Consistent Online Gaussian Process Regression Without the Sample Complexity Bottleneck.
Proceedings of the 2019 American Control Conference, 2019

Compressed Streaming Importance Sampling for Efficient Representations of Localization Distributions.
Proceedings of the 53rd Asilomar Conference on Signals, Systems, and Computers, 2019

2018
Decentralized Online Learning With Kernels.
IEEE Trans. Signal Process., 2018

Composable Learning with Sparse Kernel Representations.
Proceedings of the 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems, 2018

Parallel Stochastic Successive Convex Approximation Method for Large-Scale Dictionary Learning.
Proceedings of the 2018 IEEE International Conference on Acoustics, 2018

Exact Nonparametric Decentralized Online Optimization.
Proceedings of the 2018 IEEE Global Conference on Signal and Information Processing, 2018

Asynchronous Saddle Point Method: Interference Management Through Pricing.
Proceedings of the 57th IEEE Conference on Decision and Control, 2018

Nonparametric Stochastic Compositional Gradient Descent for Q-Learning in Continuous Markov Decision Problems.
Proceedings of the 2018 Annual American Control Conference, 2018

Decentralized Online Nonparametric Learning.
Proceedings of the 52nd Asilomar Conference on Signals, Systems, and Computers, 2018

On Stream-Centric Learning for Internet of Battlefield Things.
Proceedings of the 2018 AAAI Spring Symposia, 2018

2017
Proximity Without Consensus in Online Multiagent Optimization.
IEEE Trans. Signal Process., 2017

D4L: Decentralized Dynamic Discriminative Dictionary Learning.
IEEE Trans. Signal Inf. Process. over Networks, 2017

Decentralized Prediction-Correction Methods for Networked Time-Varying Convex Optimization.
IEEE Trans. Autom. Control., 2017

Large-scale nonconvex stochastic optimization by Doubly Stochastic Successive Convex approximation.
Proceedings of the 2017 IEEE International Conference on Acoustics, 2017

Decentralized efficient nonparametric stochastic optimization.
Proceedings of the 2017 IEEE Global Conference on Signal and Information Processing, 2017

A variational approach to dual methods for constrained convex optimization.
Proceedings of the 2017 American Control Conference, 2017

Beyond consensus and synchrony in decentralized online optimization using saddle point method.
Proceedings of the 51st Asilomar Conference on Signals, Systems, and Computers, 2017

2016
A Class of Prediction-Correction Methods for Time-Varying Convex Optimization.
IEEE Trans. Signal Process., 2016

A Class of Parallel Doubly Stochastic Algorithms for Large-Scale Learning.
CoRR, 2016

Decentralized Dynamic Discriminative Dictionary Learning.
CoRR, 2016

Online learning for characterizing unknown environments in ground robotic vehicle models.
Proceedings of the 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems, 2016

Proximity without consensus in online multi-agent optimization.
Proceedings of the 2016 IEEE International Conference on Acoustics, 2016

Decentralized online optimization with heterogeneous data sources.
Proceedings of the 2016 IEEE Global Conference on Signal and Information Processing, 2016

A Quasi-newton prediction-correction method for decentralized dynamic convex optimization.
Proceedings of the 15th European Control Conference, 2016

Doubly random parallel stochastic methods for large scale learning.
Proceedings of the 2016 American Control Conference, 2016

Doubly stochastic algorithms for large-scale optimization.
Proceedings of the 50th Asilomar Conference on Signals, Systems and Computers, 2016

2015
A Saddle Point Algorithm for Networked Online Convex Optimization.
IEEE Trans. Signal Process., 2015

Regret bounds of a distributed saddle point algorithm.
Proceedings of the 2015 IEEE International Conference on Acoustics, 2015

Target tracking with dynamic convex optimization.
Proceedings of the 2015 IEEE Global Conference on Signal and Information Processing, 2015

A decentralized prediction-correction method for networked time-varying convex optimization.
Proceedings of the 6th IEEE International Workshop on Computational Advances in Multi-Sensor Adaptive Processing, 2015

Prediction-correction methods for time-varying convex optimization.
Proceedings of the 49th Asilomar Conference on Signals, Systems and Computers, 2015

Task-driven dictionary learning in distributed online settings.
Proceedings of the 49th Asilomar Conference on Signals, Systems and Computers, 2015


  Loading...