arXiv research

Study on sample complexity for pure exploration in feedback graph settings.

Study how communication and feedback graphs affect learning outcomes.

We study an online learning framework introduced by Mannor and Shamir (2011) in which the feedback is specified by a graph, in a setting where the graph may vary from round to round and is \emph{never fully revealed} to the learner. We show a large gap between the adversarial and the stochastic cases. In the adversaria…

Study of reinforcement learning with additional feedback observations.

New algorithm improves bandit with graph feedback by decomposing regret.

Neural ODEs control graph dynamics with low energy feedback.

We study the stochastic multi-armed bandit problem with the graph-based feedback structure introduced by Mannor and Shamir. We analyze the performance of the two most prominent stochastic bandit algorithms, Thompson Sampling and Upper Confidence Bound (UCB), in the graph-based feedback setting. We show that these algor…

Novel algorithms for online learning with uncertain feedback graphs reduce regret.

We consider a problem of stochastic online learning with general probabilistic graph feedback, where each directed edge in the feedback graph has probability $p_{ij}$. Two cases are covered. (a) The one-step case, where after playing arm $i$ the learner observes a sample reward feedback of arm $j$ with independent prob…

Graph-based approach repairs programs from diagnostic feedback.

We propose a novel spectral convolutional neural network (CNN) model on graph structured data, namely Distributed Feedback-Looped Networks (DFNets). This model is incorporated with a robust class of spectral graph filters, called feedback-looped filters, to provide better localization on vertices, while still attaining…

We consider stochastic multi-armed bandit problems with graph feedback, where the decision maker is allowed to observe the neighboring actions of the chosen action. We allow the graph structure to vary with time and consider both deterministic and Erdős-Rényi random graph models. For such a graph feedback model, we fir…

This paper extends combinatorial semi-bandits to graph feedback, improving regret bounds.

New algorithm reduces high-probability regret for time-varying feedback graphs.

We derive upper and lower bounds for the policy regret of $T$-round online learning problems with graph-structured feedback, where the adversary is nonoblivious but assumed to have a bounded memory. We obtain upper bounds of $\widetilde O(T^{2/3})$ and $\widetilde O(T^{3/4})$ for strongly-observable and weakly-observab…

We study the adversarial multi-armed bandit problem where partial observations are available and where, in addition to the loss incurred for each action, a \emph{switching cost} is incurred for shifting to a new action. All previously known results incur a factor proportional to the independence number of the feedback …

Paper tackles dense subgraph discovery with noisy feedback.

New graph feedback model for bandits with improved regret bounds.

We study multi-armed bandit problems with graph feedback, in which the decision maker is allowed to observe the neighboring actions of the chosen action, in a setting where the graph may vary over time and is never fully revealed to the decision maker. We show that when the feedback graphs are undirected, the original …

SBO uses dual voting to build consensus in noisy feedback settings.

Boltzmann exploration is widely used in reinforcement learning to provide a trade-off between exploration and exploitation. Recently, in (Cesa-Bianchi et al., 2017) it has been shown that pure Boltzmann exploration does not perform well from a regret perspective, even in the simplest setting of stochastic multi-armed b…

New graph types help identify complex relationships.

We study online learning when partial feedback information is provided following every action of the learning process, and the learner incurs switching costs for changing his actions. In this setting, the feedback information system can be represented by a graph, and previous works studied the expected regret of the le…

New algorithm for online learning with noisy side observations.

AGFN improves causal discovery by integrating expert feedback and handling latent confounding.

Unified framework for expert selection with bandit and lower-bound feedback.

We propose a method for solving statistical mechanics problems defined on sparse graphs. It extracts a small Feedback Vertex Set (FVS) from the sparse graph, converting the sparse system to a much smaller system with many-body and dense interactions with an effective energy on every configuration of the FVS, then learn…

While loopy belief propagation (LBP) performs reasonably well for inference in some Gaussian graphical models with cycles, its performance is unsatisfactory for many others. In particular for some models LBP does not converge, and in general when it does converge, the computed variances are incorrect (except for cycle-…

Fuzzy cognitive maps (FCMs) model feedback causal relations in interwoven webs of causality and policy variables. FCMs are fuzzy signed directed graphs that allow degrees of causal influence and event occurrence. Such causal models can simulate a wide range of policy scenarios and decision processes. Their directed loo…

Study on a new family of problems interpolating expert advice and multi-armed bandits.

Approximates cycles in planar and bounded-genus graphs.

IDS improves reinforcement learning with contextual information.

We study small-loss bounds for adversarial multi-armed bandits with graph feedback, that is, adaptive regret bounds that depend on the loss of the best arm or related quantities, instead of the total number of rounds. We derive the first small-loss bound for general strongly observable graphs, resolving an open problem…

New methods for graph completion improve image annotation and neuroimaging.

We present and study a partial-information model of online learning, where a decision maker repeatedly chooses from a finite set of actions, and observes some subset of the associated losses. This naturally models several situations where the losses of different actions are related, and knowing the loss of one action p…

Photonic co-processor speeds up training of large neural networks.

Learning the right graph representation from noisy, multisource data has garnered significant interest in recent years. A central tenet of this problem is relational learning. Here the objective is to incorporate the partial information each data source gives us in a way that captures the true underlying relationships.…

Algorithm identifies best arm in combinatorial bandits with semi-bandit feedback.

Interactive RL and DT feedback improve feature selection efficiency.

Algorithm learns to bid optimally in repeated first-price auctions with censored feedback.

A new algorithm tackles delayed combinatorial semi-bandit with causal relations.

New approach combines semi-supervised learning and bandits for better predictions.

Study local exploration on dynamic graphs with time-varying edges.

We solve structure learning for cyclic linear causal models using observational data.

MissNODAG learns cyclic causal graphs from incomplete data.

A new method for optimizing language-based agentic systems using semantic backpropagation.

We study the online influence maximization problem in social networks under the independent cascade model. Specifically, we aim to learn the set of "best influencers" in a social network online while repeatedly interacting with it. We address the challenges of (i) combinatorial action space, since the number of feasibl…

New algorithm reduces regret in combinatorial causal bandits without graph structure.