Search Results for author:
Found 9 papers, 0 papers with code
Lazarus: Resilient and Elastic Training of Mixture-of-Experts Models with Adaptive Expert Placement
The cost of even a single failure is significant, as all GPUs need to wait idle until the failure is resolved, potentially losing considerable training progress as training has to restart from checkpoints.
An Experimental Study of Quantitative Evaluations on Saliency Methods
It has been long debated that eXplainable AI (XAI) is an important technology for model and data exploration, validation, and debugging.
Discover the Hidden Attack Path in Multi-domain Cyberspace Based on Reinforcement Learning
To achieve these results, we pose discovering attack paths as a Reinforcement Learning (RL) problem and train an agent to discover multi-domain cyberspace attack paths.
Quantitative Evaluations on Saliency Methods: An Experimental Study
It has been long debated that eXplainable AI (XAI) is an important topic, but it lacks rigorous definition and fair metrics.
Ferryman at SemEval-2020 Task 7: Ensemble Model for Assessing Humor in Edited News Headlines
Natural language processing (NLP) has been applied to various fields including text classification and sentiment analysis.
Will\_go at SemEval-2020 Task 9: An Accurate Approach for Sentiment Analysis on Hindi-English Tweets Based on Bert and Pesudo Label Strategy
Mixing languages are widely used in social media, especially in multilingual societies like India.
Domain-specific Communication Optimization for Distributed DNN Training
Communication overhead poses an important obstacle to distributed DNN training and draws increasing attention in recent years.
Weakness Analysis of Cyberspace Configuration Based on Reinforcement Learning
To achieve these results, we pose finding attack paths as a Reinforcement Learning (RL) problem and train an agent to find multiple domain attack paths.
Enabling Automatic Certification of Online Auctions
This requires agents to have a deeper understanding of auction mechanisms and be able to verify desirable properties of a given mechanism.
