Related papers: $C$-$\Delta\Theta$: Circuit-Restricted Weight Arit…
Motivated by the use of high speed circuit switches in large scale data centers, we consider the problem of circuit switch scheduling. In this problem we are given demands between pairs of servers and the goal is to schedule at every time…
Test-time compute scaling allocates inference computation uniformly, uses fixed sampling strategies, and applies verification only for reranking. In contrast, we propose a verifier-guided adaptive framework treating reasoning as iterative…
The isolated toughness variant is a salient parameter for measuring the vulnerability of networks, which is inherently related to fractional factors (used to characterize the feasibility of data transmission). The combination of minimum…
In this paper, a fault-tolerant approach to mitigate transient and permanent faults of arithmetic and logic operations of embedded processors called FT-EALU is proposed. In this method, each operation is replicated in time and the derived…
Convolutional Neural Networks (ConvNets) are trained offline using the few available data and may therefore suffer from substantial accuracy loss when ported on the field, where unseen input patterns received under unpredictable external…
A new framework is developed for control of constrained nonlinear systems with structured parametric uncertainties. Forward invariance of a safe set is achieved through online parameter adaptation and data-driven model estimation. The new…
Deep reinforcement learning (DRL) techniques have become increasingly used in various fields for decision-making processes. However, a challenge that often arises is the trade-off between both the computational efficiency of the…
Adaptive test-time compute for LLM agents aims to invoke extra computation only when it improves performance. Existing methods typically use confidence-, uncertainty-, or difficulty-based gates, assuming a fixed direction from the gating…
Various mobile applications that comprise dependent tasks are gaining widespread popularity and are increasingly complex. These applications often have low-latency requirements, resulting in a significant surge in demand for computing…
The current reinforcement learning framework focuses exclusively on performance, often at the expense of efficiency. In contrast, biological control achieves remarkable performance while also optimizing computational energy expenditure and…
This thesis considers sequential decision problems, where the loss/reward incurred by selecting an action may not be inferred from observed feedback. A major part of this thesis focuses on the unsupervised sequential selection problem,…
Large language models (LLMs) are fluent but largely static after pre-training; new or shifting knowledge is typically added with retrieval-augmented generation (RAG) or fine-tuning. RAG raises latency and engineering overhead and often…
This paper presents the performance of an AC transmission switching (TS) based real-time contingency analysis (RTCA) tool that is introduced in Part I of this paper. The approach quickly proposes high quality corrective switching actions…
Safe offline reinforcement learning aims to learn policies that maximize cumulative rewards while adhering to safety constraints, using only offline data for training. A key challenge is balancing safety and performance, particularly when…
A novel perspective on the design of robust model predictive control (MPC) methods is presented, whereby closed-loop constraint satisfaction is ensured using recursive feasibility of the MPC optimization. Necessary and sufficient conditions…
To plan safely in uncertain environments, agents must balance utility with safety constraints. Safe planning problems can be modeled as a chance-constrained partially observable Markov decision process (CC-POMDP) and solutions often use…
We present RETA (Relative Timing Analysis), a differential timing analysis technique to verify the impact of an update on the execution time of embedded software. Timing analysis is computationally expensive and labor intensive. Software…
Reinforcement learning-based recommender systems have recently gained popularity. However, the design of the reward function, on which the agent relies to optimize its recommendation policy, is often not straightforward. Exploring the…
Selective prediction, where a model has the option to abstain from making a decision, is crucial for machine learning applications in which mistakes are costly. In this work, we focus on distributional regression and introduce a framework…
This paper presents the development of a novel life-extending control scheme for critical helicopter components subjected to significant fatigue loading. The primary objective is to synthesize a more efficient and less conservative…