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

We address the challenge of policy evaluation in real-world applications of reinforcement learning systems where the available historical data is limited due to ethical, practical, or security considerations. This constrained distribution…

We propose a policy improvement algorithm for Reinforcement Learning (RL) which is called Rerouted Behavior Improvement (RBI). RBI is designed to take into account the evaluation errors of the Q-function. Such errors are common in RL when…

For over a decade, processor design has focused on implementing sophisticated policies for various components of the out-of-order pipeline, including cache replacement and prefetching. The prevailing design philosophy has been to build…

Crucial performance metrics of a caching algorithm include its ability to quickly and accurately learn a popularity distribution of requests. However, a majority of work on analytical performance analysis focuses on hit probability after an…

We investigate a robust penalized logistic regression algorithm based on a minimum distance criterion. Influential outliers are often associated with the explosion of parameter vector estimates, but in the context of standard logistic…

Offline (or batch) reinforcement learning (RL) algorithms seek to learn an optimal policy from a fixed dataset without active data collection. Based on the composition of the offline dataset, two main categories of methods are used:…

We study episodic reinforcement learning (RL) in non-stationary linear kernel Markov decision processes (MDPs). In this setting, both the reward function and the transition kernel are linear with respect to the given feature maps and are…

U.S. discrimination law can impose liability on firms that fail to adopt a less discriminatory alternative (LDA): a decision policy that achieves the same business objectives while reducing disparate impact on legally protected groups.…

The increasing adoption of large language models (LLMs) necessitates inference serving systems that can deliver both high throughput and low latency. Deploying LLMs with hundreds of billions of parameters on memory-constrained GPUs exposes…

We study two model selection settings in stochastic linear bandits (LB). In the first setting, which we refer to as feature selection, the expected reward of the LB problem is in the linear span of at least one of $M$ feature maps (models).…

Large language models (LLMs) are widely deployed, but their substantial compute demands make them vulnerable to inference cost attacks that aim to deliberately maximize the output length. In this work, we investigate a distinct attack…

Logic locking (LL) has gained attention as a promising intellectual property protection measure for integrated circuits. However, recent attacks, facilitated by machine learning (ML), have shown the potential to predict the correct key in…

Off-policy policy optimization is a challenging problem in reinforcement learning (RL). The algorithms designed for this problem often suffer from high variance in their estimators, which results in poor sample efficiency, and have issues…

This paper studies the impact of DRAM writes on DDR5-based system. To efficiently perform DRAM writes, modern systems buffer write requests and try to complete multiple write operations whenever the DRAM mode is switched from read to write.…

Data selection has emerged as a core issue for large-scale visual-language model pretaining (e.g., CLIP), particularly with noisy web-curated datasets. Three main data selection approaches are: (1) leveraging external non-CLIP models to aid…

Answering multi-hop reasoning questions requires retrieving and synthesizing information from diverse sources. Large Language Models (LLMs) struggle to perform such reasoning consistently. Here we propose an approach to pinpoint and rectify…

Machine learning has become one of the main components for task automation in many application domains. Despite the advancements and impressive achievements of machine learning, it has been shown that learning algorithms can be compromised…

Visuomotor policies trained via behavior cloning are vulnerable to covariate shift, where small deviations from expert trajectories can compound into failure. Common strategies to mitigate this issue involve expanding the training…

To improve the overall performance of processors, computer architects use various performance optimization techniques in modern processors, such as speculative execution, branch prediction, and chaotic execution. Both now and in the future,…

Despite the data-rich environment in which memory systems of modern computing platforms operate, many state-of-the-art architectural policies employed in the memory system rely on static, human-designed heuristics that fail to truly adapt…