Search Results for author:
Found 53 papers, 7 papers with code
RB-Modulation: Training-Free Personalization of Diffusion Models using Stochastic Optimal Control
Existing training-free approaches exhibit difficulties in (a) style extraction from reference images in the absence of additional style or content text descriptions, (b) unwanted content leakage from reference style images, and (c) effective composition of style and content.
In-Context Learning with Transformers: Softmax Attention Adapts to Function Lipschitzness
We show that an attention unit learns a window that it uses to implement a nearest-neighbors predictor adapted to the landscape of the pretraining tasks.
Beyond First-Order Tweedie: Solving Inverse Problems using Latent Diffusion
To our best knowledge, this is the first work to offer an efficient second-order approximation in solving inverse problems using latent diffusion and editing real-world images with corruptions.
Provable Multi-Task Representation Learning by Two-Layer ReLU Neural Networks
An increasingly popular machine learning paradigm is to pretrain a neural network (NN) on many tasks offline, then adapt it to downstream tasks, often by re-training only the last linear layer of the network.
Solving Linear Inverse Problems Provably via Posterior Sampling with Latent Diffusion Models
We present the first framework to solve linear inverse problems leveraging pre-trained latent diffusion models.
Collaborative Multi-Agent Heterogeneous Multi-Armed Bandits
The study of collaborative multi-agent bandits has attracted significant attention recently.
InfoNCE Loss Provably Learns Cluster-Preserving Representations
The goal of contrasting learning is to learn a representation that preserves underlying clusters by keeping samples with similar content, e. g. the ``dogness'' of a dog, close to each other in the space generated by the representation.
Beyond Uniform Smoothness: A Stopped Analysis of Adaptive SGD
Despite the richness, an emerging line of works achieves the $\widetilde{\mathcal{O}}(\frac{1}{\sqrt{T}})$ rate of convergence when the noise of the stochastic gradients is deterministically and uniformly bounded.
A Theoretical Justification for Image Inpainting using Denoising Diffusion Probabilistic Models
To the best of our knowledge, this is the first linear convergence result for a diffusion based image inpainting algorithm.
PAC Generalization via Invariant Representations
These are representations of the covariates such that the best model on top of the representation is invariant across training environments.
Non-Stationary Bandits under Recharging Payoffs: Improved Planning with Sublinear Regret
Even assuming prior knowledge of the mean payoff functions, computing an optimal planning in the above model is NP-hard, while the state-of-the-art is a $1/4$-approximation algorithm for the case where at most one arm can be played per round.
FedAvg with Fine Tuning: Local Updates Lead to Representation Learning
We show that the reason behind generalizability of the FedAvg's output is its power in learning the common data representation among the clients' tasks, by leveraging the diversity among client data distributions via local updates.
Minimax Regret for Cascading Bandits
Cascading bandits is a natural and popular model that frames the task of learning to rank from Bernoulli click feedback in a bandit setting.
Robust Multi-Agent Bandits Over Undirected Graphs
Thus, we generalize existing regret bounds beyond the complete graph (where $d_{\text{mal}}(i) = m$), and show the effect of malicious agents is entirely local (in the sense that only the $d_{\text{mal}}(i)$ malicious agents directly connected to $i$ affect its long-term regret).
The Power of Adaptivity in SGD: Self-Tuning Step Sizes with Unbounded Gradients and Affine Variance
We study convergence rates of AdaGrad-Norm as an exemplar of adaptive stochastic gradient methods (SGD), where the step sizes change based on observed stochastic gradients, for minimizing non-convex, smooth objectives.
MAML and ANIL Provably Learn Representations
Recent empirical evidence has driven conventional wisdom to believe that gradient-based meta-learning (GBML) methods perform well at few-shot learning because they learn an expressive data representation that is shared across tasks.
Improved Algorithms for Misspecified Linear Markov Decision Processes
(P1) Its regret after $K$ episodes scales as $K \max \{ \varepsilon_{\text{mis}}, \varepsilon_{\text{tol}} \}$, where $\varepsilon_{\text{mis}}$ is the degree of misspecification and $\varepsilon_{\text{tol}}$ is a user-specified error tolerance.
Episodic Bandits with Stochastic Experts
The agent interacts with the environment over episodes, with each episode having different context distributions; this results in the `best expert' changing across episodes.
Finite-Sample Analysis of Off-Policy TD-Learning via Generalized Bellman Operators
Our key step is to show that the generalized Bellman operator is simultaneously a contraction mapping with respect to a weighted $\ell_p$-norm for each $p$ in $[1,\infty)$, with a common contraction factor.
Does Optimal Source Task Performance Imply Optimal Pre-training for a Target Task?
Fine-tuning of pre-trained deep nets is commonly used to improve accuracies and training times for neural nets.
Job Dispatching Policies for Queueing Systems with Unknown Service Rates
In multi-server queueing systems where there is no central queue holding all incoming jobs, job dispatching policies are used to assign incoming jobs to the queue at one of the servers.
Combinatorial Blocking Bandits with Stochastic Delays
Recent work has considered natural variations of the multi-armed bandit problem, where the reward distribution of each arm is a special function of the time passed since its last pulling.
Regret Bounds for Stochastic Shortest Path Problems with Linear Function Approximation
We propose an algorithm that uses linear function approximation (LFA) for stochastic shortest path (SSP).
Linear Bandit Algorithms with Sublinear Time Complexity
For sufficiently large $K$, our algorithms have sublinear per-step complexity and $\tilde O(\sqrt{T})$ regret.
Exploiting Shared Representations for Personalized Federated Learning
Based on this intuition, we propose a novel federated learning framework and algorithm for learning a shared data representation across clients and unique local heads for each client.
A Lyapunov Theory for Finite-Sample Guarantees of Asynchronous Q-Learning and TD-Learning Variants
As a by-product, by analyzing the convergence bounds of $n$-step TD and TD$(\lambda)$, we provide theoretical insights into the bias-variance trade-off, i. e., efficiency of bootstrapping in RL.
One-bit feedback is sufficient for upper confidence bound policies
We consider a variant of the traditional multi-armed bandit problem in which each arm is only able to provide one-bit feedback during each pull based on its past history of rewards.
Stochastic Linear Bandits with Protected Subspace
We study a variant of the stochastic linear bandit problem wherein we optimize a linear objective function but rewards are accrued only orthogonal to an unknown subspace (which we interpret as a \textit{protected space}) given only zero-order stochastic oracle access to both the objective itself and protected subspace.
How Does the Task Landscape Affect MAML Performance?
Model-Agnostic Meta-Learning (MAML) has become increasingly popular for training models that can quickly adapt to new tasks via one or few stochastic gradient descent steps.
Adaptive KL-UCB based Bandit Algorithms for Markovian and i.i.d. Settings
rewards are a special case of Markov rewards and it is difficult to design an algorithm that works well independent of whether the underlying model is truly Markovian or i. i. d.
Robust Multi-Agent Multi-Armed Bandits
Recent works have shown that agents facing independent instances of a stochastic $K$-armed bandit can collaborate to decrease regret.
Multi-Agent Low-Dimensional Linear Bandits
We study a multi-agent stochastic linear bandit with side information, parameterized by an unknown vector $\theta^* \in \mathbb{R}^d$.
Contextual Blocking Bandits
Assuming knowledge of the context distribution and the mean reward of each arm-context pair, we cast the problem as an online bipartite matching problem, where the right-vertices (contexts) arrive stochastically and the left-vertices (arms) are blocked for a finite number of rounds each time they are matched.
On Under-exploration in Bandits with Mean Bounds from Confounded Data
We study a variant of the multi-armed bandit problem where side information in the form of bounds on the mean of each arm is provided.
Task-Robust Model-Agnostic Meta-Learning
Meta-learning methods have shown an impressive ability to train models that rapidly learn new tasks.
Finite-Sample Analysis of Stochastic Approximation Using Smooth Convex Envelopes
In particular, we use it to establish the first-known convergence rate of the V-trace algorithm for off-policy TD-learning.
The Gossiping Insert-Eliminate Algorithm for Multi-Agent Bandits
Agents use the communication medium to recommend only arm-IDs (not samples), and thus update the set of arms from which they play.
Verification and Parameter Synthesis for Stochastic Systems using Optimistic Optimization
As a consequence, we obtain theoretical regret bounds on sample efficiency of our solution that depends on key problem parameters like smoothness, near-optimality dimension, and batch size.
Social Learning in Multi Agent Multi Armed Bandits
Our setting consists of a large number of agents $n$ that collaboratively and simultaneously solve the same instance of $K$ armed MAB to minimize the average cumulative regret over all agents.
Blocking Bandits
We show that with prior knowledge of the rewards and delays of all the arms, the problem of optimizing cumulative reward does not admit any pseudo-polynomial time algorithm (in the number of arms) unless randomized exponential time hypothesis is false, by mapping to the PINWHEEL scheduling problem.
Mix and Match: An Optimistic Tree-Search Approach for Learning Models from Mixture Distributions
We consider a covariate shift problem where one has access to several different training datasets for the same learning problem and a small validation set which possibly differs from all the individual training distributions.
Noisy Blackbox Optimization with Multi-Fidelity Queries: A Tree Search Approach
We study the problem of black-box optimization of a noisy function in the presence of low-cost approximations or fidelities, which is motivated by problems like hyper-parameter tuning.
Applications of Common Entropy for Causal Inference
We study the problem of discovering the simplest latent variable that can make two observed discrete variables conditionally independent.
Multi-Fidelity Black-Box Optimization with Hierarchical Partitions
Motivated by settings such as hyper-parameter tuning and physical simulations, we consider the problem of black-box optimization of a function.
Importance Weighted Generative Networks
Deep generative networks can simulate from a complex target distribution, by minimizing a loss with respect to samples from that distribution.
Contextual Bandits with Stochastic Experts
We consider the problem of contextual bandits with stochastic experts, which is a variation of the traditional stochastic contextual bandit with experts problem.
Model-Powered Conditional Independence Test
We consider the problem of non-parametric Conditional Independence testing (CI testing) for continuous random variables.
Identifying Best Interventions through Online Importance Sampling
Motivated by applications in computational advertising and systems biology, we consider the problem of identifying the best out of several possible soft interventions at a source node $V$ in an acyclic causal directed graph, to maximize the expected value of a target node $Y$ (located downstream of $V$).
Regret of Queueing Bandits
A naive view of this problem would suggest that queue-regret should grow logarithmically: since queue-regret cannot be larger than classical regret, results for the standard MAB problem give algorithms that ensure queue-regret increases no more than logarithmically in time.
The Search Problem in Mixture Models
We consider the task of learning the parameters of a {\em single} component of a mixture model, for the case when we are given {\em side information} about that component, we call this the "search problem" in mixture models.
Contextual Bandits with Latent Confounders: An NMF Approach
Our algorithm achieves a regret of $\mathcal{O}\left(L\mathrm{poly}(m, \log K) \log T \right)$ at time $T$, as compared to $\mathcal{O}(LK\log T)$ for conventional contextual bandits, assuming a constant gap between the best arm and the rest for each context.
Online Collaborative-Filtering on Graphs
We consider this problem under a simple natural model, wherein the number of items and the number of item-views are of the same order, and an `access-graph' constrains which user is allowed to see which item.
Localized epidemic detection in networks with overwhelming noise
Our algorithm requires only local-neighbor knowledge of this graph, and in a broad array of settings that we describe, succeeds even when false negatives and false positives make up an overwhelming fraction of the data available.
