Ming Jin

Screening of Effectiveness Evaluation Index and Construction of Network Index System of Command and Control System

2019 · 2019 IEEE 3rd Information Technology, Networking, Electronic and Automation Control Conference (ITNEC)

Based on the comprehensive evaluation index of the force system, this paper chooses effectiveness evaluation indicators of command and control system extensively which include 5 first-level indicators, 11 second-level indicators and 86 bottom-level indicators. Firstly, …

Learning Neural Networks under Input-Output Specifications

2022 · arXiv (Cornell University)

In this paper, we examine an important problem of learning neural networks that certifiably meet certain specifications on input-output behaviors. Our strategy is to find an inner approximation of the set of admissible policy parameters, …

LAVA: Data Valuation without Pre-Specified Learning Algorithms

2023 · arXiv (Cornell University)

Traditionally, data valuation (DV) is posed as a problem of equitably splitting the validation performance of a learning algorithm among the training data. As a result, the calculated data values depend on many design choices …

Tempo Adaptation in Non-stationary Reinforcement Learning

2023 · arXiv (Cornell University)

We first raise and tackle a ``time synchronization'' issue between the agent and the environment in non-stationary reinforcement learning (RL), a crucial factor hindering its real-world applications. In reality, environmental changes occur over wall-clock time …

The Mirrored Influence Hypothesis: Efficient Data Influence Estimation by Harnessing Forward Passes

2024

Large-scale black-box models have become ubiquitous across numerous applications. Understanding the influence of individual training data sources on predictions made by these models is crucial for improving their trustworthiness. Current influence estimation techniques involve computing …