Performance Bound

Performance bounds research aims to establish limits on the achievable performance of algorithms and models across various domains, from object recognition to reinforcement learning. Current efforts focus on developing tighter bounds by accounting for inherent data noise (e.g., annotation errors), improving approximation algorithms for computationally complex problems, and leveraging deep learning techniques to learn instance-specific structures for enhanced performance prediction. These advancements are crucial for evaluating algorithm efficacy, guiding future research directions, and ultimately improving the reliability and efficiency of machine learning systems in diverse applications.

Papers

September 14, 2024

Label Convergence: Defining an Upper Performance Bound in Object Recognition through Contradictory Annotations
David Tschirschwitz, Volker Rodehorst
Label Noise Object Recognition Model Accuracy Performance Bound

May 23, 2024

Mobile Robot Sensory Coverage in 2-D Environments: An Optimization Approach with Efficiency Bounds
E. Fourney, J. W. Burdick, E. D. Rimon
Mobile Robot Coverage Path Planning Optimal Sensor Dimensional Environment Performance Bound Sensory Coverage

February 21, 2024

Performance Improvement Bounds for Lipschitz Configurable Markov Decision Processes
Alberto Maria Metelli
Markov Decision Process Performance Bound

September 20, 2023

Using deep learning to construct stochastic local search SAT solvers with performance bounds
Maximilian Kramer, Paul Boes
Deep Learning Local Search Satisfiability Solver Boolean Satisfiability Problem Performance Bound

April 19, 2023

Bridging RL Theory and Practice with the Effective Horizon
Cassidy Laidlaw, Stuart Russell, Anca Dragan
Reinforcement Learning Deep Reinforcement Learning Practice Mode Reinforcement Learning Benchmark Performance Bound

February 2, 2023

Performance Bounds for Policy-Based Average Reward Reinforcement Learning Algorithms
Yashaswini Murthy, Mehrdad Moharrami, R. Srikant
Reinforcement Learning Algorithm Approximate Policy Iteration Average Reward Reinforcement Learning Performance Bound Average Reward MDPs

May 10, 2022

A Closer Look at Blind Super-Resolution: Degradation Models, Baselines, and Performance Upper Bounds
Wenlong Zhang, Guangyuan Shi, Yihao Liu, Chao Dong, Xiao-Ming Wu
Baseline Result Glance Annotation Blind Super Resolution Degradation Model Performance Bound

December 28, 2021

Efficient Performance Bounds for Primal-Dual Reinforcement Learning from Demonstrations
Angeliki Kamoutsi, Goran Banjac, John Lygeros
Inverse Reinforcement Learning Noisy Demonstration Policy Optimization Stochastic Convex Optimization Low Regret Performance Bound Primal Dual Reinforcement Learning

Performance Bound

Papers

Label Convergence: Defining an Upper Performance Bound in Object Recognition through Contradictory Annotations

Mobile Robot Sensory Coverage in 2-D Environments: An Optimization Approach with Efficiency Bounds

Performance Improvement Bounds for Lipschitz Configurable Markov Decision Processes

Using deep learning to construct stochastic local search SAT solvers with performance bounds

Bridging RL Theory and Practice with the Effective Horizon

Performance Bounds for Policy-Based Average Reward Reinforcement Learning Algorithms

A Closer Look at Blind Super-Resolution: Degradation Models, Baselines, and Performance Upper Bounds

Efficient Performance Bounds for Primal-Dual Reinforcement Learning from Demonstrations