Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,657 papers · 148 categories

Trend · papers per month

85170254339 · Jun 202019922001200920172026
48 results for Time-varying feedback graphs

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

problem High-probability regret bounds for adversarial bandits with time-varying feedback graphs.
method Online mirror descent framework with innovative techniques for pessimistic loss estimators.
result Achieves optimal high-probability regret bound for general and weakly observable graphs.

The paper develops methods for time-varying constrained online convex optimization.

problem Time-varying loss and constraint functions in online convex optimization.
method Model-based augmented Lagrangian methods (MALM) for time-varying and delayed feedback.
result Sublinear regret and constraint violation for both time-varying and delayed feedback scenarios.

New algorithm reduces dynamic regret in time-varying movement costs.

problem Dynamic regret in online convex optimization with time-varying movement costs.
method Introduced a novel algorithm for time-varying movement costs, achieving comparator-adaptive dynamic regret bound.
result Established first comparator-adaptive dynamic regret bound of O~((M2+MPT)(T+tλt))\widetilde{\mathcal{O}}(\sqrt{(M^2+MP_T)(T+\sum_t λ_t)}).

Proposes estimators for complex dose-response curves using kernel methods.

problem Estimating complex dose-response curves with continuous treatments, mediators, and covariates.
method Kernel ridge regression with sequential kernel embedding technique.
result Simple estimators for mediated and time-varying dose response curves with nonasymptotic uniform rates.

Adaptive ML learns complex time-varying systems without new data.

problem Applying ML to time-varying systems with shifting distributions.
method Mapping high-dimensional inputs to low-dimensional latent space, actively tuning latent space based on feedback.
result Learning correlations and tracking system evolution in real-time without new data.

Paper tackles dynamic graph topology identification in time-varying graphs.

problem Dynamic graph topology identification in time-varying graphs.
method Proposes an online algorithm for time-varying optimization, with intrinsic temporal regularization.
result Demonstrates performance on Gaussian graphical model problem.

A new method learns dynamic graph representations from time-varying data.

problem Learning dynamic graph representations from time-varying data.
method Higher-order skip-gram with negative sampling (HOSGNS) for tensor factorization.
result HOSGNS outperforms state-of-the-art methods in downstream tasks.

One of the cornerstones of the field of signal processing on graphs are graph filters, direct analogues of classical filters, but intended for signals defined on graphs. This work brings forth new insights on the distributed graph filtering problem. We design a family of autoregressive moving average (ARMA) recursions,…

2016-02-14abs ↗pdf ↗

No-regret optimization for time-varying functions using uncertainty injection.

problem Optimizing time-varying functions with no-regret in bandit feedback.
method W-SparQ-GP-UCB, incorporating uncertainty injection and additional queries.
result Achieves no-regret with a vanishing number of additional queries per iteration.

Study how communication and feedback graphs affect learning outcomes.

problem Understanding the impact of feedback graphs on cooperative online learning.
method Analyzed network regret in terms of the independence number of the strong product of communication and feedback graphs.
result Proved bounds for network regret and demonstrated the non-improvable nature of positive results in pathological cases.

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…

2016-05-23abs ↗pdf ↗

Study of reinforcement learning with additional feedback observations.

problem Episodic reinforcement learning in Markov decision processes with feedback observations.
method Formalization of feedback graph, model-based algorithms leveraging feedback, regret bound analysis.
result Regret bound depends only on the size of the maximum acyclic subgraph of the feedback graph.

From social networks to Internet applications, a wide variety of electronic communication tools are producing streams of graph data; where the nodes represent users and the edges represent the contacts between them over time. This has led to an increased interest in mechanisms to model the dynamic structure of time-var…

2014-03-14abs ↗pdf ↗

DynDepNet learns dynamic brain graphs from fMRI data for better prediction performance.

problem Static brain graphs from fMRI data lead to poor GNN performance.
method Dynamic Graph Structure Learning for time-varying brain connectivity.
result DynDepNet achieves state-of-the-art sex classification accuracy on real-world fMRI data.

Algorithm estimates parameters over time-varying graphs without special assumptions.

problem Estimating parameters over time-varying graphs without assuming independence.
method Decentralized online regularized learning with innovation, consensus, and regularization terms.
result Estimations converge almost surely under certain conditions.

Unified framework infers time-varying graphs from incomplete signals.

problem Jointly inferring time-varying network topologies and imputing missing data from partial observations.
method Unified non-convex optimization framework with Proximal Alternating Direction Method of Multipliers (PADMM) algorithm.
result Superior robustness in high missing-data regimes, demonstrated through extensive numerical experiments.

Novel algorithm for decentralized optimization in time-varying networks with delays.

problem Decentralized optimization in networks with communication delays.
method DT-GO algorithm, applicable to general directed graphs, converges to same complexity as centralized SGD.
result Algorithm DT-GO achieves convergence rates for convex and non-convex objectives, similar to centralized SGD.

New algorithms optimize actions under time-varying constraints without projecting.

problem Optimizing actions under time-varying constraints without projecting.
method Projection-free algorithms using linear optimization oracle.
result Guaranteed ildeO(T3/4) ilde{O}(T^{3/4}) regret and O(T7/8)O(T^{7/8}) constraints violation.

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…

2019-05-23abs ↗pdf ↗

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

2019-03-04abs ↗pdf ↗

Graph-based approach repairs programs from diagnostic feedback.

problem Learning to repair programs from limited labeled data and compiler error messages.
method Introduces program-feedback graph and graph neural network for reasoning, and self-supervised learning with unlabeled programs.
result DrRepair significantly outperforms prior work, achieving high repair rates.

TV-SurvCaus improves causal inference for dynamic treatments in survival analysis.

problem Estimating causal effects of time-varying treatments on survival outcomes.
method Representation balancing techniques extended to time-varying treatment regimes with survival outcomes.
result TV-SurvCaus outperforms existing methods in estimating individualized treatment effects with time-varying covariates and treatments.

BASS efficiently learns time-varying graphs with low complexity and automatic tuning.

problem Estimating time-varying graphical models with efficient and automatic parameter tuning.
method BASS uses temporally-dependent spike-and-slab priors and variational inference to learn graph structures efficiently.
result BASS outperforms existing methods in recovering true graphs, especially for high-dimensional cases.

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…

2019-10-24abs ↗pdf ↗

We present a distributed (non-Bayesian) learning algorithm for the problem of parameter estimation with Gaussian noise. The algorithm is expressed as explicit updates on the parameters of the Gaussian beliefs (i.e. means and precision). We show a convergence rate of O(1/k)O(1/k) with the constant term depending on the numb…

2016-12-06abs ↗pdf ↗

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

problem Adversarial combinatorial semi-bandits with graph feedback.
method Introduced graph feedback in combinatorial semi-bandits, using convexified actions and online stochastic mirror descent.
result Optimal regret scales as ST+αSTS\sqrt{T}+\sqrt{αST}, interpolating between full and semi-bandit feedback.

We derive upper and lower bounds for the policy regret of TT-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 O~(T2/3)\widetilde O(T^{2/3}) and O~(T3/4)\widetilde O(T^{3/4}) for strongly-observable and weakly-observab…

2018-04-01abs ↗pdf ↗

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 …

2019-07-29abs ↗pdf ↗

Estimates time-varying network connections using multi-stage smoothing.

problem Estimating edge probabilities of time-varying networks.
method Multi-stage smoothing: temporal local smoothing followed by node-domain smoothing.
result Captures both smooth temporal evolution and structural patterns in connectivity.

Geometric framework for dynamic feedback linearization of control systems with symmetry.

problem Dynamic feedback linearization of control systems with symmetry.
method Geometric framework based on Lie symmetry, systematic procedure for all smooth, generic system trajectories.
result Sufficient condition for dynamic feedback linearizability obtained.

Attention-based GNNs can't prevent oversmoothing, leading to homogeneous node representations.

problem The issue of oversmoothing in attention-based GNNs.
method Viewed attention-based GNNs as nonlinear time-varying dynamical systems and used tools from the theory of products of inhomogeneous matrices and the joint spectral radius.
result Graph attention mechanism cannot prevent oversmoothing and loses expressive power exponentially.

This research introduces dynamic portfolio cuts using a spectral approach for graph-theoretic diversification.

problem Traditional methods for estimating asset-return covariance assume statistical time-invariance, failing to capture the nonstationary nature of asset price movements.
method Introduces graph spectral estimators that account for nonstationarity, partitioning the market graph into time-evolving clusters for dynamic portfolio cuts.
result Demonstrates the advantages of the proposed framework over traditional methods through numerical case studies using real-world price data.

Undirected graphs are often used to describe high dimensional distributions. Under sparsity conditions, the graph can be estimated using 1\ell_1 penalization methods. However, current methods assume that the data are independent and identically distributed. If the distribution, and hence the graph, evolves over time t…

2008-02-20abs ↗pdf ↗

We discuss a variant of `blind' community detection, in which we aim to partition an unobserved network from the observation of a (dynamical) graph signal defined on the network. We consider a scenario where our observed graph signals are obtained by filtering white noise input, and the underlying network is different …

2019-04-26abs ↗pdf ↗

New graph feedback model for bandits with improved regret bounds.

problem Understanding how graph structure affects regret in bandit problems.
method Introduced fractional weak domination number and kk-packing independence number to capture upper and lower bounds on regret. Used strong duality theorem to derive upper and lower bounds.
result Proved general upper and lower bounds on regret for various graph structures, showing tightness up to a logarithmic factor.

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 …

2018-05-23abs ↗pdf ↗