arXiv research

Study exact community recovery in noisy SBM with limited queries.

New protocols show 1-bit mean estimation can be order-optimal without interaction.

New algorithms learn MNL weights efficiently for any slate size.

Noise addition prevents overfitting in adaptive data analysis.

Study compares adaptive vs fixed query learning methods.

Algorithm adapts to shifting domains with minimal label queries.

Adaptive querying learns user psychometrics with AI personas.

Fairly allocate items with noisy queries, reducing envy.

In adaptive data analysis, the user makes a sequence of queries on the data, where at each step the choice of query may depend on the results in previous steps. The releases are often randomized in order to reduce overfitting for such adaptively chosen queries. In this paper, we propose a minimax framework for adaptive…

InfoTuple efficiently selects larger tuple queries for ranking multiple objects, improving efficiency and consistency.

Adapts data analysis for growing data, improving generalization guarantees.

In this paper we study the adaptive learnability of decision trees of depth at most $d$ from membership queries. This has many applications in automated scientific discovery such as drugs development and software update problem. Feldman solves the problem in a randomized polynomial time algorithm that asks $\tilde O(2^…

AdaWISH improves efficiency of discrete integration queries.

Adaptive compute allocation improves model performance by prioritizing harder queries.

This work sets lower bounds on the number of score queries needed for diffusion sampling.

In this paper, we initiate a rigorous theoretical study of clustering with noisy queries (or a faulty oracle). Given a set of $n$ elements, our goal is to recover the true clustering by asking minimum number of pairwise queries to an oracle. Oracle can answer queries of the form : "do elements $u$ and $v$ belong to the…

LAZO reduces query complexity and variance in ZO methods.

We study the problem of estimating a set of $d$ linear queries with respect to some unknown distribution $\mathbf{p}$ over a domain $\mathcal{J}=[J]$ based on a sensitive data set of $n$ individuals under the constraint of local differential privacy. This problem subsumes a wide range of estimation tasks, e.g., distrib…

The paper tackles machine unlearning by designing efficient algorithms for adaptive query classes.

Adapts large transformer model for search query intent understanding.

Study learns random hypergraphs with queries, improving on previous results.

Algorithm improves query recommendations with immediate user feedback.

In this paper we address cardinality estimation problem which is an important subproblem in query optimization. Query optimization is a part of every relational DBMS responsible for finding the best way of the execution for the given query. These ways are called plans. The execution time of different plans may differ b…

OSAMD adapts online to changing distributions with limited labels.

Adaptive truncation improves privacy in online Bayesian estimation.

Adaptive Misinformation defends against model stealing attacks by sending incorrect predictions for OOD queries.

Paper develops an efficient mean estimator for 1-bit communication constraints.

Paper proposes a 1-bit mean estimation method with near-optimal sample complexity.

We point out an issue with Theorem 5 appearing in "Group-based active query selection for rapid diagnosis in time-critical situations". Theorem 5 bounds the expected number of queries for a greedy algorithm to identify the class of an item within a constant factor of optimal. The Theorem is based on correctness of a re…

The paper tackles sequential mode estimation with oracle queries.

Study reduces memory needs for active learning with enriched queries.

Unified query framework for active metric learning and classification.

Improved algorithm for selecting a hypothesis locally privately with fewer queries.

FAQ efficiently evaluates LLMs with statistical guarantees using adaptive query selection.

New algorithm maximizes non-monotone adaptive submodular functions in linear time.

We introduce an unsupervised approach to efficiently discover the underlying features in a data set via crowdsourcing. Our queries ask crowd members to articulate a feature common to two out of three displayed examples. In addition we also ask the crowd to provide binary labels to the remaining examples based on the di…

We consider the problem of group testing with sum observations and noiseless answers, in which we aim to locate multiple objects by querying the number of objects in each of a sequence of chosen sets. We study a probabilistic setting with entropy loss, in which we assume a joint Bayesian prior density on the locations …

We show that for the problem of testing if a matrix $A \in F^{n \times n}$ has rank at most $d$, or requires changing an $ε$-fraction of entries to have rank at most $d$, there is a non-adaptive query algorithm making $\widetilde{O}(d^2/ε)$ queries. Our algorithm works for any field $F$. This improves upon the previous…

We propose a new active learning by query synthesis approach using Generative Adversarial Networks (GAN). Different from regular active learning, the resulting algorithm adaptively synthesizes training instances for querying to increase learning speed. We generate queries according to the uncertainty principle, but our…

In correlation clustering, we are given $n$ objects together with a binary similarity score between each pair of them. The goal is to partition the objects into clusters so to minimise the disagreements with the scores. In this work we investigate correlation clustering as an active learning problem: each similarity sc…

This paper explores the adaptive (active) PAC (probably approximately correct) top-$k$ ranking (i.e., top-$k$ item selection) and total ranking problems from $l$-wise ($l\geq 2$) comparisons under the multinomial logit (MNL) model. By adaptively choosing sets to query and observing the noisy output of the most favored …

Datasets are often reused to perform multiple statistical analyses in an adaptive way, in which each analysis may depend on the outcomes of previous analyses on the same dataset. Standard statistical guarantees do not account for these dependencies and little is known about how to provably avoid overfitting and false d…

We study active learning where the labeler can not only return incorrect labels but also abstain from labeling. We consider different noise and abstention conditions of the labeler. We propose an algorithm which utilizes abstention responses, and analyze its statistical consistency and query complexity under fairly nat…

Study exact partition recovery with same-cluster oracle, bounded error.

Proposes a new OAL algorithm for imbalanced data with limited labels.

CEGA addresses GNN security by enabling cost-effective model acquisition.

AdvMind detects adversary intent in black-box attacks with high accuracy.

Proposes an online model for LLM cascading with adaptive API selection.