Related papers: Making Belady-Inspired Replacement Policies More E…

Learning Markov decision processes (MDPs) in the presence of the adversary is a challenging problem in reinforcement learning (RL). In this paper, we study RL in episodic MDPs with adversarial reward and full information feedback, where the…

We study high-dimensional multi-armed contextual bandits with batched feedback where the $T$ steps of online interactions are divided into $L$ batches. In specific, each batch collects data according to a policy that depends on previous…

As capacity and complexity of on-chip cache memory hierarchy increases, the service cost to the critical loads from Last Level Cache (LLC), which are frequently repeated, has become a major concern. The processor may stall for a…

This article introduces a novel family of decentralised caching policies, applicable to wireless networks with finite storage at the edge-nodes (stations). These policies, that are based on the Least-Recently-Used replacement principle, are…

3D NAND flash memory with advanced multi-level cell techniques provides high storage density, but suffers from significant performance degradation due to a large number of read-retry operations. Although the read-retry mechanism is…

Many Information Centric Networking (ICN) proposals use a network of caches to bring the contents closer to the consumers, reduce the load on producers and decrease the unnecessary retransmission for ISPs. Nevertheless, the existing cache…

LLMs are increasingly used world-wide from daily tasks to agentic systems and data analytics, requiring significant GPU resources. LLM inference systems, however, are slow compared to database systems, and inference performance and…

Spin-Transfer Torque RAM (STTRAM) is promising for cache applications. However, it brings new data security issues that were absent in volatile memory counterparts such as Static RAM (SRAM) and embedded Dynamic RAM (eDRAM). This is…

It is generally observed that the fraction of live lines in shared last-level caches (SLLC) is very small for chip multiprocessors (CMPs). This can be tackled using promotion-based replacement policies like re-reference interval prediction…

We consider the offline reinforcement learning (RL) setting where the agent aims to optimize the policy solely from the data without further environment interactions. In offline RL, the distributional shift becomes the primary source of…

State-of-the-art techniques for addressing scaling-related main memory errors identify and repair bits that are at risk of error from within the memory controller. Unfortunately, modern main memory chips internally use on-die error…

Multi-task reinforcement learning aims to quickly identify solutions for new tasks with minimal or no additional interaction with the environment. Generalized Policy Improvement (GPI) addresses this by combining a set of base policies to…

We study the problem of learning-based attacks in linear systems, where the communication channel between the controller and the plant can be hijacked by a malicious attacker. We assume the attacker learns the dynamics of the system from…

Adapting language models (LMs) to new tasks via post-training carries the risk of degrading existing capabilities -- a phenomenon classically known as catastrophic forgetting. In this paper, toward identifying guidelines for mitigating this…

Reinforcement learning (RL) is a fundamental framework for sequential decision-making, in which an agent learns an optimal policy through interactions with an unknown environment. In settings with function approximation, many existing RL…

Unforeseen particle accelerator interruptions, also known as interlocks, lead to abrupt operational changes despite being necessary safety measures. These may result in substantial loss of beam time and perhaps even equipment damage. We…

The overall performance of content distribution networks as well as recently proposed information-centric networks rely on both memory and bandwidth capacities. In this framework, the hit ratio is the key performance indicator which…

Cause-effect chains, as a widely used modeling method in real-time embedded systems, are extensively applied in various safety-critical domains. End-to-end latency, as a key real-time attribute of cause-effect chains, is crucial in many…

The primary goal of my Ph.D. study is to develop provably efficient and practical algorithms for data-driven sequential decision-making under uncertainty. My work focuses on reinforcement learning (RL), multi-armed bandits, and their…

Unbiased recommender learning (URL) and off-policy evaluation/learning (OPE/L) techniques are effective in addressing the data bias caused by display position and logging policies, thereby consistently improving the performance of…