arXiv subjects

Christina Fragouli

Publications and source records attributed to Christina Fragouli.

At least 19 recordsLinked to original sources

arXiv2026

Mixing Makes Markovian Contexts Cheap for Linear Bandits

Recent work shows that when contexts are drawn i.i.d., linear contextual bandits can be reduced to single-context linear bandits. This ``contexts are cheap'' perspective is highly advantageous, as it allows for sharper finite-time analyses and leverages mature techniques from the linear bandit literature, such as those for misspecification and adversarial corruption. However, this reduction crucially relies on the independence of contexts and does not extend to settings with temporally correlated (e.g., Markovian) contexts, which arise frequently in practice. Motivated by applications with temporally correlated availability, we extend this perspective to linear bandits with Markovian context processes, where the action set evolves via an exogenous Markov chain. Our main contribution is a reduction that applies under uniform geometric ergodicity. We construct a stationary surrogate action set to solve the problem using a standard linear bandit oracle, employing a delayed-update scheme to control the bias induced by the nonstationary conditional context distributions. We further provide a phased algorithm for unknown stationary distributions that learns the surrogate mapping online. In both settings, we obtain a high-probability worst-case regret bound matching that of the underlying linear bandit oracle in sufficiently fast mixing regimes. We then validate our results on a real-world instance, where we show practical gains over a LinUCB baseline.

cs.LG↗

arXiv2026

A Recommendation System Approach for Interference-Robust Sensor Subset Selection

This paper develops a method for sensor-subset selection for tracking. Prior work showed that low-cost acoustic Received Signal Strength Indicator (RSSI) measurements can be used to recommend subsets of sensor nodes whose expensive sensing modalities, such as cameras, can achieve high tracking accuracy. While efficient, RSSI-based approaches are challenged by acoustic interference. We propose a recommendation-system-inspired framework that instead leverages frequency-band acoustic features and a Two-Tower Multi-Layer Perceptron (MLP) architecture to efficiently score candidate sensor subsets. Experimental results on outdoor vehicle-tracking deployments show that the proposed method can improve accuracy by around 20\% over the RSSI baseline while maintaining the low computational overhead required for real-time selective sensing.

cs.LG↗

arXiv2026

Top-P Sensor Selection for Target Localization

We study set-valued decision rules in which performance is defined by the inclusion of the top-$p$ hypotheses, rather than only the single best or true hypothesis. This criterion is motivated by sensor selection for target tracking, where inexpensive measurements are used to identify a list of sensor nodes that are likely to be closest to a target. We analyze the performance of top-$p$ versus top-$1$ selection under sequential hypothesis testing, propose a geometry-aware sensor selection algorithm, and validate the approach using real testbed data.

cs.IT↗

arXiv2026

Best-Arm Identification with Noisy Actuation

In this paper, we consider a multi-armed bandit (MAB) instance and study how to identify the best arm when arm commands are conveyed from a central learner to a distributed agent over a discrete memoryless channel (DMC). Depending on the agent capabilities, we provide communication schemes along with their analysis, which interestingly relate to the zero-error capacity of the underlying DMC.

cs.IT↗

arXiv2026

ScaleBITS: Scalable Bitwidth Search for Hardware-Aligned Mixed-Precision LLMs

Post-training weight quantization is crucial for reducing the memory and inference cost of large language models (LLMs), yet pushing the average precision below 4 bits remains challenging due to highly non-uniform weight sensitivity and the lack of principled precision allocation. Existing solutions use irregular fine-grained mixed-precision with high runtime overhead or rely on heuristics or highly constrained precision allocation strategies. In this work, we propose ScaleBITS, a mixed-precision quantization framework that enables automated, fine-grained bitwidth allocation under a memory budget while preserving hardware efficiency. Guided by a new sensitivity analysis, we introduce a hardware-aligned, block-wise weight partitioning scheme, powered by bi-directional channel reordering. We formulate global bitwidth allocation as a constrained optimization problem and develop a scalable approximation to the greedy algorithm, enabling end-to-end principled allocation. Experiments show that ScaleBITS significantly improves over uniform-precision quantization (up to +36%) and outperforms state-of-the-art sensitivity-aware baselines (up to +13%) in ultra-low-bit regime, without adding runtime overhead.

cs.LG↗

arXiv2025

ICQuant: Index Coding enables Low-bit LLM Quantization

The rapid deployment of Large Language Models (LLMs) highlights the need for efficient low-bit post-training quantization (PTQ), due to their high memory costs. A key challenge in weight quantization is the presence of outliers, which inflate quantization ranges and lead to large errors. While a number of outlier suppression techniques have been proposed, they either: fail to effectively shrink the quantization range, or incur (relatively) high bit overhead. In this paper, we present ICQuant, a novel framework that leverages outlier statistics to design an efficient index coding scheme for outlier-aware weight-only quantization. Compared to existing outlier suppression techniques requiring $\approx 1$ bit overhead to halve the quantization range, ICQuant requires only $\approx 0.3$ bits; a significant saving in extreme compression regimes (e.g., 2-3 bits per weight). ICQuant can be used on top of any existing quantizers to eliminate outliers, improving the quantization quality. Using just 2.3 bits per weight and simple scalar quantizers, ICQuant improves the zero-shot accuracy of the 2-bit Llama3-70B model by up to 130% and 150% relative to QTIP and QuIP#; and it achieves comparable performance to the best-known fine-tuned quantizer (PV-tuning) without fine-tuning.

cs.LG↗

arXiv2025

Two-Level Priority Coding for Resilience to Arbitrary Blockage Patterns

Ultra-reliable low-latency communication is essential in mission-critical settings, including military applications, where persistent and asymmetric link blockages caused by mobility, jamming, or adversarial attacks can disrupt delay-sensitive transmissions. This paper addresses this challenge by deploying a multilevel diversity coding (MDC) scheme that controls the received information, offers distinct reliability guarantees based on the priority of data streams, and maintains low design and operational complexity as the number of network paths increases. For two priority levels over three edge-disjoint paths, the complete capacity region is characterized, showing that superposition coding achieves the region in general, whereas network coding is required only in a specific corner case. Moreover, sufficient conditions under which a simple superposition coding scheme achieves the capacity for an arbitrary number of paths are identified. To prove these results and provide a unified analytical framework, the problem of designing high-performing MDC schemes is shown to be equivalent to the problem of designing high-performing encoding schemes over a class of broadcast networks, referred to as combination networks in the literature.

cs.IT↗

arXiv2025

Enhancing Binary Search via Overlapping Partitions

This paper considers the task of performing binary search under noisy decisions, focusing on the application of target area localization. In the presence of noise, the classical partitioning approach of binary search is prone to error propagation due to the use of strictly disjoint splits. While existing works on noisy binary search propose techniques such as query repetition or probabilistic updates to mitigate errors, they often lack explicit mechanisms to manage the trade-off between error probability and search complexity, with some providing only asymptotic guarantees. To address this gap, we propose a binary search framework with tunable overlapping partitions, which introduces controlled redundancy into the search process to enhance robustness against noise. We analyze the performance of the proposed algorithm in both discrete and continuous domains for the problem of area localization, quantifying how the overlap parameter impacts the trade-off between search tree depth and error probability. Unlike previous methods, this approach allows for direct control over the balance between reliability and efficiency. Our results emphasize the versatility and effectiveness of the proposed method, providing a principled extension to existing noisy search paradigms and enabling new insights into the interplay between partitioning strategies and measurement reliability.

cs.IT↗

arXiv2025

Does Feedback Help in Bandits with Arm Erasures?

We study a distributed multi-armed bandit (MAB) problem over arm erasure channels, motivated by the increasing adoption of MAB algorithms over communication-constrained networks. In this setup, the learner communicates the chosen arm to play to an agent over an erasure channel with probability $ε\in [0,1)$; if an erasure occurs, the agent continues pulling the last successfully received arm; the learner always observes the reward of the arm pulled. In past work, we considered the case where the agent cannot convey feedback to the learner, and thus the learner does not know whether the arm played is the requested or the last successfully received one. In this paper, we instead consider the case where the agent can send feedback to the learner on whether the arm request was received, and thus the learner exactly knows which arm was played. Surprisingly, we prove that erasure feedback does not improve the worst-case regret upper bound order over the previously studied no-feedback setting. In particular, we prove a regret lower bound of $Ω(\sqrt{KT} + K / (1 - ε))$, where $K$ is the number of arms and $T$ the time horizon, that matches no-feedback upper bounds up to logarithmic factors. We note however that the availability of feedback enables simpler algorithm designs that may achieve better constants (albeit not better order) regret bounds; we design one such algorithm and evaluate its performance numerically.

cs.LG↗

arXiv2024

Common Information Dimension

The exact common information between a set of random variables $X_1,...,X_n$ is defined as the minimum entropy of a shared random variable that allows for the exact distributive simulation of $X_1,...,X_n$. It has been established that, in certain instances, infinite entropy is required to achieve distributive simulation, suggesting that continuous random variables may be needed in such scenarios. However, to date, there is no established metric to characterize such cases. In this paper, we propose the concept of Common Information Dimension (CID) with respect to a given class of functions $\mathcal{F}$, defined as the minimum dimension of a random variable $W$ required to distributively simulate a set of random variables $X_1,...,X_n$, such that $W$ can be expressed as a function of $X_1,\cdots,X_n$ using a member of $\mathcal{F}$. Our main contributions include the computation of the common information dimension for jointly Gaussian random vectors in a closed form, with $\mathcal{F}$ being the linear functions class.

cs.IT↗

arXiv2024

Learning for Bandits under Action Erasures

We consider a novel multi-arm bandit (MAB) setup, where a learner needs to communicate the actions to distributed agents over erasure channels, while the rewards for the actions are directly available to the learner through external sensors. In our model, while the distributed agents know if an action is erased, the central learner does not (there is no feedback), and thus does not know whether the observed reward resulted from the desired action or not. We propose a scheme that can work on top of any (existing or future) MAB algorithm and make it robust to action erasures. Our scheme results in a worst-case regret over action-erasure channels that is at most a factor of $O(1/\sqrt{1-ε})$ away from the no-erasure worst-case regret of the underlying MAB algorithm, where $ε$ is the erasure probability. We also propose a modification of the successive arm elimination algorithm and prove that its worst-case regret is $\Tilde{O}(\sqrt{KT}+K/(1-ε))$, which we prove is optimal by providing a matching lower bound.

stat.ML↗

arXiv2024

Multi-Agent Bandit Learning through Heterogeneous Action Erasure Channels

Multi-Armed Bandit (MAB) systems are witnessing an upswing in applications within multi-agent distributed environments, leading to the advancement of collaborative MAB algorithms. In such settings, communication between agents executing actions and the primary learner making decisions can hinder the learning process. A prevalent challenge in distributed learning is action erasure, often induced by communication delays and/or channel noise. This results in agents possibly not receiving the intended action from the learner, subsequently leading to misguided feedback. In this paper, we introduce novel algorithms that enable learners to interact concurrently with distributed agents across heterogeneous action erasure channels with different action erasure probabilities. We illustrate that, in contrast to existing bandit algorithms, which experience linear regret, our algorithms assure sub-linear regret guarantees. Our proposed solutions are founded on a meticulously crafted repetition protocol and scheduling of learning across heterogeneous channels. To our knowledge, these are the first algorithms capable of effectively learning through heterogeneous action erasure channels. We substantiate the superior performance of our algorithm through numerical experiments, emphasizing their practical significance in addressing issues related to communication constraints and delays in multi-agent environments.

cs.LG↗

arXiv2024

Achieving Low Latency at Low Outage: Multilevel Coding for mmWave Channels

Millimeter-wave (mmWave) spectrum is expected to support data-intensive applications that require ultra-reliable low-latency communications (URLLC). However, mmWave links are highly sensitive to blockage, which may lead to disruptions in the communication. Traditional techniques that build resilience against such blockages (among which are interleaving and feedback mechanisms) incur delays that are too large to effectively support URLLC. This calls for novel techniques that ensure resilient URLLC. In this paper, we propose to deploy multilevel codes over space and over time. These codes offer several benefits, such as they allow to control what information is received and they provide different reliability guarantees for different information streams based on their priority. We also show that deploying these codes leads to attractive trade-offs between rate, delay, and outage probability. A practically-relevant aspect of the proposed technique is that it offers resilience while incurring a low operational complexity.

cs.IT↗

arXiv2023

Supporting Passive Users in mmWave Networks

The interference from active to passive users is a well-recognized challenge in millimeter-wave (mmWave) communications. We propose a method that enables to limit the interference on passive users (whose presence may not be detected since they do not transmit) with a small penalty to the throughput of active users. Our approach abstracts away (in a simple, yet informative way) the physical layer component and it leverages the directivity of mmWave links and the available network path diversity. We provide linear programming formulations, lower bounds on active users rates, numerical evaluations, and we establish a connection with the problem of (information theoretically) secure communication over mmWave networks.

cs.IT↗

arXiv2023

Contexts can be Cheap: Solving Stochastic Contextual Bandits with Linear Bandit Algorithms

In this paper, we address the stochastic contextual linear bandit problem, where a decision maker is provided a context (a random set of actions drawn from a distribution). The expected reward of each action is specified by the inner product of the action and an unknown parameter. The goal is to design an algorithm that learns to play as close as possible to the unknown optimal policy after a number of action plays. This problem is considered more challenging than the linear bandit problem, which can be viewed as a contextual bandit problem with a \emph{fixed} context. Surprisingly, in this paper, we show that the stochastic contextual problem can be solved as if it is a linear bandit problem. In particular, we establish a novel reduction framework that converts every stochastic contextual linear bandit instance to a linear bandit instance, when the context distribution is known. When the context distribution is unknown, we establish an algorithm that reduces the stochastic contextual instance to a sequence of linear bandit instances with small misspecifications and achieves nearly the same worst-case regret bound as the algorithm that solves the misspecified linear bandit instances. As a consequence, our results imply a $O(d\sqrt{T\log T})$ high-probability regret bound for contextual linear bandits, making progress in resolving an open problem in (Li et al., 2019), (Li et al., 2021). Our reduction framework opens up a new way to approach stochastic contextual linear bandit problems, and enables improved regret bounds in a number of instances including the batch setting, contextual bandits with misspecifications, contextual bandits with sparse unknown parameters, and contextual bandits with adversarial corruption.

stat.ML↗

arXiv2023

A Diagonal Splitting Algorithm for Adaptive Group Testing

Group testing enables to identify infected individuals in a population using a smaller number of tests than individual testing. To achieve this, group testing algorithms commonly assume knowledge of the number of infected individuals; nonadaptive and several adaptive algorithms fall in this category. Some adaptive algorithms, like binary splitting, operate without this assumption, but require a number of stages that may scale linearly with the size of the population. In this paper we contribute a new algorithm that enables a balance between the number of tests and the number of stages used, and which we term diagonal group testing. Diagonal group testing, like binary splitting, does not require knowledge of the number of infected individuals, yet unlike binary splitting, is order-optimal w.r.t. the expected number of tests it requires and is guaranteed to succeed in a small number of stages that scales at most logarithmically with the size of the population. Numerical evaluations, for diagonal group testing and a hybrid approach we propose, support our theoretical findings.

cs.IT↗

arXiv2022

Proactive Resilient Transmission and Scheduling Mechanisms for mmWave Networks

This paper aims to develop resilient transmission mechanisms to suitably distribute traffic across multiple paths in an arbitrary millimeter-wave (mmWave) network. The main contributions include: (a) the development of proactive transmission mechanisms that build resilience against network disruptions in advance, while achieving a high end-to-end packet rate; (b) the design of a heuristic path selection algorithm that efficiently selects (in polynomial time in the network size) multiple proactively resilient paths with high packet rates; and (c) the development of a hybrid scheduling algorithm that combines the proposed path selection algorithm with a deep reinforcement learning (DRL) based online approach for decentralized adaptation to blocked links and failed paths. To achieve resilience to link failures, a state-of-the-art Soft Actor-Critic DRL algorithm, which adapts the information flow through the network, is investigated. The proposed scheduling algorithm robustly adapts to link failures over different topologies, channel and blockage realizations while offering a superior performance to alternative algorithms.

cs.IT↗

arXiv2022

Differentially Private Stochastic Linear Bandits: (Almost) for Free

In this paper, we propose differentially private algorithms for the problem of stochastic linear bandits in the central, local and shuffled models. In the central model, we achieve almost the same regret as the optimal non-private algorithms, which means we get privacy for free. In particular, we achieve a regret of $\tilde{O}(\sqrt{T}+\frac{1}ε)$ matching the known lower bound for private linear bandits, while the best previously known algorithm achieves $\tilde{O}(\frac{1}ε\sqrt{T})$. In the local case, we achieve a regret of $\tilde{O}(\frac{1}ε{\sqrt{T}})$ which matches the non-private regret for constant $ε$, but suffers a regret penalty when $ε$ is small. In the shuffled model, we also achieve regret of $\tilde{O}(\sqrt{T}+\frac{1}ε)$ %for small $ε$ as in the central case, while the best previously known algorithm suffers a regret of $\tilde{O}(\frac{1}ε{T^{3/5}})$. Our numerical evaluation validates our theoretical results.

cs.LG↗