We consider the problem of controlling an unknown linear dynamical system under a stochastic convex cost and full feedback of both the state and cost function. We present a computationally eﬃcient algorithm that attains an optimal √ 𝑇 regret-rate compared to the best stabilizing linear controller in hindsight. In contrast to previous work, our algorithm is based on the Optimism in the Face of Uncertainty paradigm. This results in a substantially improved computational complexity and a simpler analysis.

Efficient Online Linear Control with Stochastic Convex Costs and Unknown Dynamics

This paper investigates the problem of regret minimization in linear time-varying (LTV) dynamical systems. Due to the simultaneous presence of uncertainty and non-stationarity, designing online control algorithms for unknown LTV systems remains a challenging task. At a cost of NP-hard ofﬂine planning, prior works have introduced online convex optimization algorithms, although they suffer from nonparametric rate of regret. In this paper, we propose the ﬁrst computationally tractable online algorithm with regret guarantees that avoids ofﬂine planning over the state linear feedback policies. Our algorithm is based on the optimism in the face of uncertainty (OFU) principle in which we optimistically select the best model in a high conﬁdence region. Our algorithm is then more explorative when compared to previous approaches. To overcome non-stationarity, we propose either a restarting strategy (R-OFU) or a sliding window (SW-OFU) strategy. With proper conﬁguration, our algorithm is attains sublinear regret O ( T 2 / 3 ) . These algorithms utilize data from the current phase for tracking variations on the system dynamics. We corroborate our theoretical ﬁndings with numerical experiments, which highlight the effectiveness of our methods. To the best of our knowledge, our study establishes the ﬁrst model-based online algorithm with regret guarantees under LTV dynamical systems.

Learning to Control under Time-Varying Environment

In this work, we explore robust model-free reinforcement learning algorithms for environments that may be dynamic or even adversarial. Conventional state-based policies fail to accommodate the challenge imposed by the presence of unmodeled disturbances in such settings. Additionally, optimizing linear state-based policies pose obstacle for efficient optimization, leading to nonconvex objectives even in benign environments like linear dynamical systems. Drawing inspiration from recent advancements in model-based control, we introduce a novel class of policies centered on disturbance signals. We define several categories of these signals, referred to as pseudo-disturbances, and corresponding policy classes based on them. We provide efficient and practical algorithms for optimizing these policies. Next, we examine the task of online adaptation of reinforcement learning agents to adversarial disturbances. Our methods can be integrated with any black-box model-free approach, resulting in provable regret guarantees if the underlying dynamics is linear. We evaluate our method over different standard RL benchmarks and demonstrate improved robustness.

Online Nonstochastic Model-Free Reinforcement Learning

This paper studies online nonstochastic control problems with adversarial and static constraints. We propose online nonstochastic control algorithms that achieve both sublinear regret and sublinear adversarial constraint violation while keeping static constraint violation minimal against the optimal constrained linear control policy in hindsight. To establish the results, we introduce an online convex optimization with memory framework under adversarial and static constraints, which serves as a subroutine for the constrained online nonstochastic control algorithms. This subroutine also achieves the state-of-the-art regret and constraint violation bounds for constrained online convex optimization problems, which is of independent interest. Our experiments demonstrate the proposed control algorithms are adaptive to adversarial constraints and achieve smaller cumulative costs and violations. Moreover, our algorithms are less conservative and achieve significantly smaller cumulative costs than the state-of-the-art algorithm.

Online Nonstochastic Control with Adversarial and Static Constraints

We consider a collection of linear stochastic bandit problems, each modeling the random response of different agents to proposed interventions, coupled together by a global safety constraint. We assume a central coordinator must choose actions to play on each bandit with the objective of regret minimization, while also ensuring that the expected response of all agents satisfies the global safety constraints at each round, in spite of uncertainty about the bandits' parameters. The agents consider their observed responses to be private and in order to protect their sensitive information, the data sharing with the central coordinator is performed under local differential privacy (LDP). However, providing higher level of privacy to different agents would have consequences in terms of safety and regret. We formalize these tradeoffs by building on the notion of the sharpness of the safety set - a measure of how the geometric properties of the safe set affects the growth of regret - and propose a unilaterally unimprovable vector of privacy levels for different agents given a maximum regret budget.

pdf/the-safety-privacy-tradeoff-in-linear-bandits-obsquaoicyr0.pdf

The Safety-Privacy Tradeoff in Linear Bandits

Algorithmic fairness has emerged as a critical concern in artificial intelligence (AI) research. However, the development of fair AI systems is not an objective process. Fairness is an inherently subjective concept, shaped by the values, experiences, and identities of those involved in research and development. To better understand the norms and values embedded in current fairness research, we conduct a meta-analysis of algorithmic fairness papers from two leading conferences on AI fairness and ethics, AIES and FAccT, covering a final sample of 139 papers over the period from 2018 to 2022. Our investigation reveals two concerning trends: first, a US-centric perspective dominates throughout fairness research; and second, fairness studies exhibit a widespread reliance on binary codifications of human identity (e.g.,"Black/White","male/female"). These findings highlight how current research often overlooks the complexities of identity and lived experiences, ultimately failing to represent diverse global contexts when defining algorithmic bias and fairness. We discuss the limitations of these research design choices and offer recommendations for fostering more inclusive and representative approaches to fairness in AI systems, urging a paradigm shift that embraces nuanced, global understandings of human identity and values.

(Unfair) Norms in Fairness Research: A Meta-Analysis

Electrodermal activity (EDA) is a measure of sympathetic arousal that has been linked to depression in laboratory experiments. However, the inability to measure EDA passively over time and in the real-world has limited conclusions that can be drawn about EDA as an indicator of mental health status outside of controlled settings. Recent smartwatches have begun to incorporate wrist-worn continuous EDA sensors that enable longitudinal measurement of sympathetic arousal in every-day life. This work (N=237, 4-week observation period) examines the association between passively collected, diurnal variations in EDA and symptoms of depression, anxiety and perceived stress in a large community sample. Subjects who exhibited elevated depressive and anxiety symptoms had higher tonic EDA, skin temperature, and heart rate, despite not engaging in greater physical activity, compared to those that were not depressed or anxious. In contrast, subjects who exhibited elevated stress only exhibited higher skin temperature. Most strikingly, differences in EDA between those with high versus low symptoms were most prominent during the early morning. We did not observe amplitude or phase differences in the diurnal patterns. Our work suggests that electrodermal sensors may be practical and useful in measuring the physiological correlates of mental health symptoms in free-living contexts and that recent consumer smartwatches might be a tool for doing so.

Evidence of Differences in Diurnal Electrodermal, Temperature, and Heart Rate Patterns by Mental Health Status in Free-Living Data

Learning with User-Level Differential Privacy Under Fixed Compute Budgets

Rapid progress in scalable, commoditized tools for data collection and data processing has made it possible for firms and policymakers to employ ever more complex metrics as guides for decision-making. These developments have highlighted a prevailing challenge -- deciding *which* metrics to compute. In particular, a firm's ability to compute a wider range of existing metrics does not address the problem of *unknown unknowns*, which reflects informational limitations on the part of the firm. To guide the choice of metrics in the face of this informational problem, we turn to the evaluated agents themselves, who may have more information than a principal about how to measure outcomes effectively. We model this interaction as a simple agency game, where we ask: *When does an agent have an incentive to reveal the observability of a cost-correlated variable to the principal?* There are two effects: better information reduces the agent's information rents but also makes some projects go forward that otherwise would fail. We show that the agent prefers to reveal information that exposes a strong enough differentiation between high and low costs. Expanding the agent's action space to include the ability to *garble* their information, we show that the agent often prefers to garble over full revelation. Still, giving the agent the ability to garble can lead to higher total welfare. Our model has analogies with price discrimination, and we leverage some of these synergies to analyze total welfare.

Information Elicitation in Agency Games

Handle everyday research tasks with reliable, citation-backed results

Your personal Research Agent to handle research tasks with citation-backed results

Popular Tasks used by Researchers

How can I help with your research?

Meet SciSpace

Get more enhanced response by uploading the PDFs you want me to reference.

No relevant PDFs in your library

SciSpace is the AI research assistant for academics. Run systematic literature reviews on 280M+ papers, and write papers with cited sources. Trusted by 1M+ students, PhDs & researchers.

SciSpace | AI for Research

Analyze PDFs

Code & Manuscripts

Funding & Grants

Literature & Patents

Medical & Clinical Data

Systematic Review

Visualize & Present

Web & Data

Build a Google Scholar-like website for your research.

Build a website

Create charts and images for your research

Create a Chart

Write a paper for submission to a journal

Draft a manuscript

Patent Search

Design eye-catching scientific posters in minutes.

Scientific Poster Generation

Systematic Literature Review

One task is running at the moment. Your messages will be shown right after.

Drag and drop or click here to browse

Loved by <highlight>1 million+</highlight> researchers

Extract a list of specific topics and their sources from unstructured text

Topics

Compare and analyze relevant papers that matches with your search

Papers

Get insights from PDFs and bookmarked papers from your library

My library

Recent searches

Try searching for:

Catch AI-generated content in scholarly and non-scholarly content

{ai} Detector

Ai Writer

Get PDF Summaries, highlighted text explanations 

Chat with PDF

Effortlessly create in-text citations and bibliographies in APA and 2,500 other formats

Citation generator

Get explanations, summaries, and answers on academic papers

Ease up your research workflow with {scispace}'s cohort of exciting AI tools

Elevate your academic writing skills and convey your ideas the way you want

Paraphraser

Explore our range of reading and writing tools

Your file is being prepared and should be ready in a few minutes. If it's a large file, it might take a bit longer. You can close this window, and we'll email you the file when it's done.

You have reached a maximum limit of <strong>{limit}</strong> columns in the table. Remove at least <strong>1</strong> column to add or create another one.

Google Research

Author Tools

Chat about Author