Related papers: $C$-$\Delta\Theta$: Circuit-Restricted Weight Arit…
Multi-turn interaction remains challenging for online reinforcement learning. A common solution is trajectory-level optimization, which treats each trajectory as a single training sample. However, this approach can be inefficient and yield…
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,…
Proactive autoscaling for containerized workloads depends on knowing the provisioning delay, i.e., the time between a scaling decision and the moment new capacity is ready to serve traffic. In practice, this cold-start duration can vary…
Two-stage recommender systems first choose a candidate generator and then rank items within the generated set. Because the generator decides which items are available to the ranker, changing the generator changes both the policy value and…
In applying reinforcement learning (RL) to high-stakes domains, quantitative and qualitative evaluation using observational data can help practitioners understand the generalization performance of new policies. However, this type of…
Constrained Markov Decision Processes are a class of stochastic decision problems in which the decision maker must select a policy that satisfies auxiliary cost constraints. This paper extends upper confidence reinforcement learning for…
It is now widely accepted that the CMOS technology implementing irreversible logic will hit a scaling limit beyond 2016, and that the increased power dissipation is a major limiting factor. Reversible computing can potentially require…
Multirotors play a significant role in diverse field robotics applications but remain highly susceptible to actuator failures, leading to rapid instability and compromised mission reliability. While various fault-tolerant control (FTC)…
We study the design of risk-sensitive online algorithms, in which risk measures are used in the competitive analysis of randomized online algorithms. We introduce the CVaR$_\delta$-competitive ratio ($\delta$-CR) using the conditional…
The Constrained Markov Decision Process (CMDP) formulation allows to solve safety-critical decision making tasks that are subject to constraints. While CMDPs have been extensively studied in the Reinforcement Learning literature, little…
Predictive coding (PC) is a general theory of cortical function. The local, gradient-based learning rules found in one kind of PC model have recently been shown to closely approximate backpropagation. This finding suggests that this…
Contextual online decision-making problems with constraints appear in a wide range of real-world applications, such as adaptive experimental design under safety constraints, personalized recommendation with resource limits, and dynamic…
In many data-driven online decision systems, actions determine not only operational costs but also the data availability for future learning -- a phenomenon termed Prediction-Induced Censoring (PIC). This challenge is particularly acute in…
Online nonparametric estimators are gaining popularity due to their efficient computation and competitive generalization abilities. An important example includes variants of stochastic gradient descent. These algorithms often take one…
Safety in reinforcement learning is often specified through cumulative cost constraints, but these trajectory-level guarantees do not directly prevent unsafe individual decisions, especially under nonstationarity. In continual and…
Large Reasoning Models (LRMs) achieve strong performance on mathematical reasoning tasks but remain unreliable on challenging instances. Existing test-time scaling methods, such as repeated sampling, self-correction, and tree search,…
The isolation level Multiversion Read Committed (RC), offered by many database systems, is known to trade consistency for increased transaction throughput. Sometimes, transaction workloads can be safely executed under RC obtaining the…
Test-time adaptation (TTA) aims to correct performance degradation of deep models under distribution shifts by updating models or inputs using unlabeled test data. Input-only diffusion-based TTA methods improve robustness for classification…
Class-Incremental Learning (CIL) aims to learn new classes sequentially while retaining the knowledge of previously learned classes. Recently, pre-trained models (PTMs) combined with parameter-efficient fine-tuning (PEFT) have shown…
Federated Learning (FL) has gained attention for addressing data scarcity and privacy concerns. While parallel FL algorithms like FedAvg exhibit remarkable performance, they face challenges in scenarios with diverse network speeds and…