Search Results for author:
Found 67 papers, 26 papers with code
Adversarial Combinatorial Bandits with Switching Costs
The lower bound for bandit feedback is $ \tilde{\Omega}\big( (\lambda K)^{\frac{1}{3}} (TI)^{\frac{2}{3}}\big)$ while that for semi-bandit feedback is $ \tilde{\Omega}\big( (\lambda K I)^{\frac{1}{3}} T^{\frac{2}{3}}\big)$ where $I$ is the number of base arms in the combinatorial arm played in each round.
Multi-Armed Bandits with Abstention
Our results offer valuable quantitative insights into the benefits of the abstention option, laying the groundwork for further exploration in other online decision-making problems with such an option.
Fixed-Budget Differentially Private Best Arm Identification
We study best arm identification (BAI) in linear bandits in the fixed-budget regime under differential privacy constraints, when the arm rewards are supported on the unit interval.
Towards Accurate Guided Diffusion Sampling through Symplectic Adjoint Method
However, since the off-the-shelf pre-trained networks are trained on clean images, the one-step estimation procedure of the clean image may be inaccurate, especially in the early stages of the generation process in diffusion models.
Fixed-Budget Best-Arm Identification in Sparse Linear Bandits
For fixed sparsity $s$ and budget $T$, the exponent in the error probability of Lasso-OD depends on $s$ but not on the dimension $d$, yielding a significant performance improvement for sparse and high-dimensional linear bandits.
Learning Regularized Graphon Mean-Field Games with Unknown Graphons
Second, using kernel embedding of distributions, we design efficient algorithms to estimate the transition kernels, reward functions, and graphons from sampled agents.
Optimal Best Arm Identification with Fixed Confidence in Restless Bandits
It is shown that under every policy, the state-action visitation proportions satisfy a specific approximate flow conservation constraint and that these proportions match the optimal proportions dictated by the lower bound under any asymptotically optimal policy.
Blink: Link Local Differential Privacy in Graph Neural Networks via Bayesian Estimation
Graph neural networks (GNNs) have gained an increasing amount of popularity due to their superior capability in learning node embeddings for various graph inference tasks, but training them can raise privacy concerns.
AdjointDPM: Adjoint Sensitivity Method for Gradient Backpropagation of Diffusion Probabilistic Models
Existing customization methods require access to multiple reference examples to align pre-trained diffusion probabilistic models (DPMs) with user-provided concepts.
Deep Unrolling for Nonconvex Robust Principal Component Analysis
We design algorithms for Robust Principal Component Analysis (RPCA) which consists in decomposing a matrix into the sum of a low rank matrix and a sparse matrix.
DragDiffusion: Harnessing Diffusion Models for Interactive Point-based Image Editing
In this work, we extend this editing framework to diffusion models and propose a novel approach DragDiffusion.
Communication-Constrained Bandits under Additive Gaussian Noise
We study a distributed stochastic multi-armed bandit where a client supplies the learner with communication-constrained feedback based on the rewards for the corresponding arm pulls.
Probably Anytime-Safe Stochastic Combinatorial Semi-Bandits
Under this constraint, we design and analyze an algorithm {\sc PASCombUCB} that minimizes the regret over the horizon of time $T$.
Minimizing the Accumulated Trajectory Error to Improve Dataset Distillation
To mitigate the adverse impact of this accumulated trajectory error, we propose a novel approach that encourages the optimization algorithm to seek a flat trajectory.
Fast Beam Alignment via Pure Exploration in Multi-armed Bandits
The beam alignment (BA) problem consists in accurately aligning the transmitter and receiver beams to establish a reliable communication link in wireless communication systems.
How Does Pseudo-Labeling Affect the Generalization Error of the Semi-Supervised Gibbs Algorithm?
Our findings offer new insights that the generalization performance of SSL with pseudo-labeling is affected not only by the information between the output hypothesis and input training data but also by the information {\em shared} between the {\em labeled} and {\em pseudo-labeled} data samples.
Federated Best Arm Identification with Heterogeneous Clients
Furthermore, we show that for any algorithm whose upper bound on the expected stopping time matches with the lower bound up to a multiplicative constant ({\em almost-optimal} algorithm), the ratio of any two consecutive communication time instants must be {\em bounded}, a result that is of independent interest.
Towards Understanding and Mitigating Dimensional Collapse in Heterogeneous Federated Learning
To remedy this problem caused by the data heterogeneity, we propose {\sc FedDecorr}, a novel method that can effectively mitigate dimensional collapse in federated learning.
Relational Reasoning via Set Transformers: Provable Efficiency and Applications to MARL
The cooperative Multi-A gent R einforcement Learning (MARL) with permutation invariant agents framework has achieved tremendous empirical successes in real-world applications.
Almost Cost-Free Communication in Federated Best Arm Identification
The local best arm at a client is the arm with the largest mean among the arms local to the client, whereas the global best arm is the arm with the largest average mean across all the clients.
Sharpness-Aware Training for Free
Intuitively, SAF achieves this by avoiding sudden drops in the loss in the sharp local minima throughout the trajectory of the updates of the weights.
A Survey of Risk-Aware Multi-Armed Bandits
In several applications such as clinical trials and financial portfolio optimization, the expected value (or the average reward) does not satisfactorily capture the merits of a drug or a portfolio.
Best Arm Identification in Restless Markov Multi-Armed Bandits
For this problem, we derive the first-known problem instance-dependent asymptotic lower bound on the growth rate of the expected time required to find the index of the best arm, where the asymptotics is as the error probability vanishes.
Optimal Clustering with Bandit Feedback
This paper considers the problem of online clustering with bandit feedback.
Almost Optimal Variance-Constrained Best Arm Identification
We design and analyze VA-LUCB, a parameter-free algorithm, for identifying the best arm under the fixed-confidence setup and under a stringent constraint that the variance of the chosen arm is strictly smaller than a given threshold.
Towards Adversarially Robust Deep Image Denoising
Secondly, to robustify DIDs, we propose an adversarial training strategy, hybrid adversarial training ({\sc HAT}), that jointly trains DIDs with adversarial and non-adversarial noisy data to ensure that the reconstruction quality is high and the denoisers around non-adversarial data are locally smooth.
Mimicking the Oracle: An Initial Phase Decorrelation Approach for Class Incremental Learning
Specifically, we experimentally show that directly encouraging CIL Learner at the initial phase to output similar representations as the model jointly trained on all classes can greatly boost the CIL performance.
Active-LATHE: An Active Learning Algorithm for Boosting the Error Exponent for Learning Homogeneous Ising Trees
We design and analyze an algorithm Active Learning Algorithm for Trees with Homogeneous Edge (Active-LATHE), which surprisingly boosts the error exponent by at least 40\% when $\rho$ is at least $0. 8$.
Achieving the Pareto Frontier of Regret Minimization and Best Arm Identification in Multi-Armed Bandits
We study the Pareto frontier of two archetypal objectives in multi-armed bandits, namely, regret minimization (RM) and best arm identification (BAI) with a fixed horizon.
Efficient Sharpness-aware Minimization for Improved Training of Neural Networks
Recently, the relation between the sharpness of the loss landscape and the generalization error has been established by Foret et al. (2020), in which the Sharpness Aware Minimizer (SAM) was proposed to mitigate the degradation of the generalization.
Information-Theoretic Characterization of the Generalization Error for Iterative Semi-Supervised Learning
Using information-theoretic principles, we consider the generalization error (gen-error) of iterative semi-supervised learning (SSL) algorithms that iteratively generate pseudo-labels for a large amount of unlabelled data to progressively refine the model parameters.
A Unifying Theory of Thompson Sampling for Continuous Risk-Averse Bandits
This paper unifies the design and the analysis of risk-averse Thompson sampling algorithms for the multi-armed bandit problem for a class of risk functionals $\rho$ that are continuous and dominant.
Robustifying Algorithms of Learning Latent Trees with Vector Variables
The optimalities of the robust version of CLRG and NJ are verified by comparing their sample complexities and the impossibility result.
Minimax Optimal Fixed-Budget Best Arm Identification in Linear Bandits
We study the problem of best arm identification in linear bandits in the fixed-budget setting.
Exact Recovery in the General Hypergraph Stochastic Block Model
This paper investigates fundamental limits of exact recovery in the general d-uniform hypergraph stochastic block model (d-HSBM), wherein n nodes are partitioned into k disjoint communities with relative sizes (p1,..., pk).
Adversarially-Trained Nonnegative Matrix Factorization
We consider an adversarially-trained version of the nonnegative matrix factorization, a popular latent dimensionality reduction technique.
CIFS: Improving Adversarial Robustness of CNNs via Channel-wise Importance-based Feature Selection
By comparing \textit{non-robust} (normally trained) and \textit{robustified} (adversarially trained) models, we observe that adversarial training (AT) robustifies CNNs by aligning the channel-wise activations of adversarial data with those of their natural counterparts.
SGA: A Robust Algorithm for Partial Recovery of Tree-Structured Graphical Models with Noisy Samples
We provide error exponent analyses and extensive numerical results on a variety of trees to show that the sample complexity of SGA is significantly better than the algorithm of Katiyar et al. (2020).
Risk-Constrained Thompson Sampling for CVaR Bandits
The multi-armed bandit (MAB) problem is a ubiquitous decision-making problem that exemplifies the exploration-exploitation tradeoff.
Probabilistic Sequential Shrinking: A Best Arm Identification Algorithm for Stochastic Bandits with Corruptions
When the amount of corruptions per step (CPS) is below a threshold, PSS($u$) identifies the best arm or item with probability tending to $1$ as $T\rightarrow \infty$.
Positive Semidefinite Matrix Factorization: A Connection with Phase Retrieval and Affine Rank Minimization
In this work, we provide a collection of tools for PSDMF, by showing that PSDMF algorithms can be designed based on phase retrieval (PR) and affine rank minimization (ARM) algorithms.
MC2G: An Efficient Algorithm for Matrix Completion with Social and Item Similarity Graphs
In this paper, we design and analyze MC2G (Matrix Completion with 2 Graphs), an algorithm that performs matrix completion in the presence of social and item similarity graphs.
Exact Asymptotics for Learning Tree-Structured Graphical Models with Side Information: Noiseless and Noisy Samples
In this case, we show that they strictly improve on the recent results of Nikolakakis, Kalogerias, and Sarwate [Proc.
RAIN: A Simple Approach for Robust and Accurate Image Classification Networks
However, similar to existing preprocessing-based methods, the randomized process will degrade the prediction accuracy.
Optimal Change-Point Detection with Training Sequences in the Large and Moderate Deviations Regimes
This paper investigates a novel offline change-point detection problem from an information-theoretic perspective.
Thompson Sampling Algorithms for Mean-Variance Bandits
The multi-armed bandit (MAB) problem is a classical learning task that exemplifies the exploration-exploitation tradeoff.
Tight Regret Bounds for Noisy Optimization of a Brownian Motion
We consider the problem of Bayesian optimization of a one-dimensional Brownian motion in which the $T$ adaptively chosen observations are corrupted by Gaussian noise.
Best Arm Identification for Cascading Bandits in the Fixed Confidence Setting
Finally, extensive numerical simulations corroborate the efficacy of CascadeBAI as well as the tightness of our upper bound on its time complexity.
Community Detection and Matrix Completion with Social and Item Similarity Graphs
We consider the problem of recovering a binary rating matrix as well as clusters of users and items based on a partially observed matrix together with side-information in the form of social and item similarity graphs.
Sequential Classification with Empirically Observed Statistics
Motivated by real-world machine learning applications, we consider a statistical classification task in a sequential setting where test samples arrive sequentially.
Economy Statistical Recurrent Units For Inferring Nonlinear Granger Causality
We make a case that the network topology of Granger causal relations is directly inferrable from a structured sparse estimate of the internal parameters of the SRU networks trained to predict the processes$'$ time series measurements.
On Robustness of Neural Ordinary Differential Equations
We then provide an insightful understanding of this phenomenon by exploiting a certain desirable property of the flow of a continuous-time ODE, namely that integral curves are non-intersecting.
Unsupervised Image Noise Modeling with Self-Consistent GAN
They jointly facilitate unsupervised learning of a noise model for various noise types.
Analysis of Optimization Algorithms via Sum-of-Squares
Program., 145(1):451--482, 2014], a powerful framework for determining convergence rates of first-order optimization algorithms.
A Ranking Model Motivated by Nonnegative Matrix Factorization with Applications to Tennis Tournaments
We propose a novel ranking model that combines the Bradley-Terry-Luce probability model with a nonnegative matrix factorization framework to model and uncover the presence of latent variables that influence the performance of top tennis players.
Distributionally Robust and Multi-Objective Nonnegative Matrix Factorization
We propose to use Lagrange duality to judiciously optimize for a set of weights to be used within the framework of the weighted-sum approach, that is, we minimize a single objective function which is a weighted sum of the all objective functions.
Thompson Sampling Algorithms for Cascading Bandits
While Thompson sampling (TS) algorithms have been shown to be empirically superior to Upper Confidence Bound (UCB) algorithms for cascading bandits, theoretical guarantees are only known for the latter.
Second-Order Asymptotically Optimal Statistical Classification
Motivated by real-world machine learning applications, we analyze approximations to the non-asymptotic fundamental limits of statistical classification.
Lower Bounds on the Bayes Risk of the Bayesian BTL Model with Applications to Comparison Graphs
In particular, we employ the Bayesian BTL model which allows for meaningful prior assumptions and to cope with situations where the number of objects is large and the number of comparisons between some objects is small or even zero.
Stochastic L-BFGS: Improved Convergence Rates and Practical Acceleration Strategies
We revisit the stochastic limited-memory BFGS (L-BFGS) algorithm.
The Informativeness of K -Means for Learning Mixture Models
These results provide intuition for the informativeness of $k$-means (with and without dimensionality reduction) as an algorithm for learning mixture models.
Rank-One NMF-Based Initialization for NMF and Relative Error Bounds under a Geometric Assumption
We propose a geometric assumption on nonnegative data matrices such that under this assumption, we are able to provide upper bounds (both deterministic and probabilistic) on the relative error of nonnegative matrix factorization (NMF).
A Unified Convergence Analysis of the Multiplicative Update Algorithm for Regularized Nonnegative Matrix Factorization
The multiplicative update (MU) algorithm has been extensively used to estimate the basis and coefficient matrices in nonnegative matrix factorization (NMF) problems under a wide range of divergences and regularizers.
Online Nonnegative Matrix Factorization with General Divergences
We develop a unified and systematic framework for performing online nonnegative matrix factorization under a wide variety of important divergences.
Online Nonnegative Matrix Factorization with Outliers
We propose a unified and systematic framework for performing online nonnegative matrix factorization in the presence of outliers.
Adversarial Top-$K$ Ranking
We study the top-$K$ ranking problem where the goal is to recover the set of top-$K$ ranked items out of a large collection of items based on partially revealed preferences.
Automatic Relevance Determination in Nonnegative Matrix Factorization with the β-Divergence
This paper addresses the estimation of the latent dimensionality in nonnegative matrix factorization (NMF) with the \beta-divergence.
