English
Related papers

Related papers: QFlip: An Adaptive Reinforcement Learning Strategy…

200 papers

Clinical AI systems frequently suffer performance decay post-deployment due to temporal data shifts, such as evolving populations, diagnostic coding updates (e.g., ICD-9 to ICD-10), and systemic shocks like the COVID-19 pandemic. Addressing…

Applications · Statistics 2026-01-22 Xin Xiong , Zijian Guo , Haobo Zhu , Chuan Hong , Jordan W Smoller , Tianxi Cai , Molei Liu

Binary security has increasingly relied on deep learning to reason about malware behavior and program semantics. However, the performance often degrades as threat landscapes evolve and code representations shift. While continual learning…

Machine Learning · Computer Science 2026-04-24 Yiling He , Junchi Lei , Hongyu She , Shuo Shao , Xinran Zheng , Yiping Liu , Zhan Qin , Lorenzo Cavallaro

Federated learning is a distributed machine learning technology, which realizes the balance between data privacy protection and data sharing computing. To protect data privacy, feder-ated learning learns shared models by locally executing…

Machine Learning · Computer Science 2023-06-26 Tianyu Zhao , Junping Du , Yingxia Shao , Zeli Guan

Balancing exploration and conservatism in the constrained setting is an important problem if we are to use reinforcement learning for meaningful tasks in the real world. In this paper, we propose a principled algorithm for safe exploration…

Artificial Intelligence · Computer Science 2023-04-24 Alexander W. Goodall , Francesco Belardinelli

While large language models (LLMs) have emerged as powerful decision-makers across a wide range of single-agent and stationary environments, fewer efforts have been devoted to settings where LLMs must engage in \emph{repeated} and…

Multiagent Systems · Computer Science 2026-02-27 Xiangyu Liu , Di Wang , Zhe Feng , Aranyak Mehta

Reasoning methods that adaptively allocate test-time compute have advanced LLM performance on easy to verify domains such as math and code. In this work, we study how to utilize this approach to train models that exhibit a degree of…

Machine Learning · Computer Science 2025-10-28 Taeyoun Kim , Fahim Tajwar , Aditi Raghunathan , Aviral Kumar

Despite considerable progress, ab initio protein structure prediction remains suboptimal. A crowdsourcing approach is the online puzzle video game Foldit, that provided several useful results that matched or even outperformed…

Biomolecules · Quantitative Biology 2020-11-09 Dimitra N. Panou , Martin Reczko

Restless multi-armed bandits (RMAB) play a central role in modeling sequential decision making problems under an instantaneous activation constraint that at most B arms can be activated at any decision epoch. Each restless arm is endowed…

Machine Learning · Computer Science 2024-05-03 Guojun Xiong , Jian Li

Motivated by emerging applications such as live-streaming e-commerce, promotions and recommendations, we introduce and solve a general class of non-stationary multi-armed bandit problems that have the following two features: (i) the…

Machine Learning · Statistics 2021-12-23 David Simchi-Levi , Zeyu Zheng , Feng Zhu

Existing works show that augmenting the training data of pre-trained language models (PLMs) for classification tasks fine-tuned via parameter-efficient fine-tuning methods (PEFT) using both clean and adversarial examples can enhance their…

Computation and Language · Computer Science 2024-06-18 Tuc Nguyen , Thai Le

Elimination algorithms for bandit identification, which prune the plausible correct answers sequentially until only one remains, are computationally convenient since they reduce the problem size over time. However, existing elimination…

Machine Learning · Computer Science 2022-10-25 Andrea Tirinzoni , Rémy Degenne

Reinforcement learning algorithms, just like any other Machine learning algorithm pose a serious threat from adversaries. The adversaries can manipulate the learning algorithm resulting in non-optimal policies. In this paper, we analyze the…

Machine Learning · Computer Science 2021-03-12 Aqeel Anwar , Arijit Raychowdhury

Extensive research demonstrates that Deep Reinforcement Learning (DRL) models are susceptible to adversarially constructed inputs (i.e., adversarial examples), which can mislead the agent to take suboptimal or unsafe actions. Recent methods…

Machine Learning · Computer Science 2026-02-24 Shenghong He

This paper introduces an approach to Reinforcement Learning Algorithm by comparing their immediate rewards using a variation of Q-Learning algorithm. Unlike the conventional Q-Learning, the proposed algorithm compares current reward with…

Machine Learning · Computer Science 2010-09-15 Punit Pandey , Deepshikha Pandey , Shishir Kumar

The critical assessment presented within this paper explores existing research pertaining to the Advanced Persistent Threat (APT) branch of cyber security, applying the knowledge extracted from this research to discuss, evaluate and…

Cryptography and Security · Computer Science 2020-04-23 Mohammad Bilal Khan

The fine-tuning of pre-trained language models has a great success in many NLP fields. Yet, it is strikingly vulnerable to adversarial examples, e.g., word substitution attacks using only synonyms can easily fool a BERT-based sentiment…

Computation and Language · Computer Science 2021-12-23 Xinhsuai Dong , Luu Anh Tuan , Min Lin , Shuicheng Yan , Hanwang Zhang

Quadrotor control policies can be trained with high performance using the exact gradients of the rewards to directly optimize policy parameters via backpropagation-through-time (BPTT). However, designing a fully differentiable reward…

Robotics · Computer Science 2025-05-22 Fanxing Li , Fangyu Sun , Tianbao Zhang , Danping Zou

In this paper, we explore the susceptibility of the independent Q-learning algorithms (a classical and widely used multi-agent reinforcement learning method) to strategic manipulation of sophisticated opponents in normal-form games played…

Computer Science and Game Theory · Computer Science 2024-07-17 Yuksel Arslantas , Ege Yuceel , Muhammed O. Sayin

A dynamic algorithm against an adaptive adversary is required to be correct when the adversary chooses the next update after seeing the previous outputs of the algorithm. We obtain faster dynamic algorithms against an adaptive adversary and…

Data Structures and Algorithms · Computer Science 2021-11-09 Amos Beimel , Haim Kaplan , Yishay Mansour , Kobbi Nissim , Thatchaphol Saranurak , Uri Stemmer

Despite the conventional wisdom that proactive security is superior to reactive security, we show that reactive security can be competitive with proactive security as long as the reactive defender learns from past attacks instead of…

Cryptography and Security · Computer Science 2015-05-14 Adam Barth , Benjamin I. P. Rubinstein , Mukund Sundararajan , John C. Mitchell , Dawn Song , Peter L. Bartlett