arXiv research

The paper tests properties of trees in graphical models using covariance queries.

We study the problem of recovering the structure underlying large Gaussian graphical models or, more generally, partial correlation graphs. In high-dimensional problems it is often too costly to store the entire sample covariance matrix. We propose a new input model in which one can query single entries of the covarian…

Noise addition prevents overfitting in adaptive data analysis.

Estimates covariance matrices using Markov chain Monte Carlo with improved sample complexity.

New insights on active sequential prediction for mean estimation.

Bayesian optimization enhanced with conformal prediction for better outcome reliability.

A new method for private query release using Johnson-Lindenstrauss projection.

Improved efficient robust regression with near-linear time and subquadratic samples.

Proposes an offline active learning method for graphs.

New SQ lower bounds show learning mixtures of bounded covariance Gaussians is hard.

Paper develops online statistical inference methods for stochastic optimization using Kiefer-Wolfowitz algorithms.

Solving sequential decision prediction problems, including those in imitation learning settings, requires mitigating the problem of covariate shift. The standard approach, DAgger, relies on capturing expert behaviour in all states that the agent reaches. In real-world settings, querying an expert is costly. We propose …

Statistical Query lower bound shows difficulty in list-decodable linear regression.

Transformers improve with Fourier integral attentions.

Oracle-efficient algorithms reduce combinatorial semi-bandit regret to logarithmic time.

New approach mitigates feedback divergence in imitation learning.

HMC improves Gaussian sampling efficiency with long, random steps.

A new framework for efficient sequence maps using Bayesian filtering and covariance.

Lower bounds show learning mixtures of linear classifiers is nearly impossible.

CRUMB: Efficient Prior Fitted Network Inference via Distributionally Matched Context Batching

A classical problem in causal inference is that of matching, where treatment units need to be matched to control units based on covariate information. In this work, we propose a method that computes high quality almost-exact matches for high-dimensional categorical datasets. This method, called FLAME (Fast Large-scale …

DiPriMe forests use private medians to create balanced tree splits for privacy-protected data.

Learning predictive models from small high-dimensional data sets is a key problem in high-dimensional statistics. Expert knowledge elicitation can help, and a strong line of work focuses on directly eliciting informative prior distributions for parameters. This either requires considerable statistical expertise or is l…

New perspective on distribution shift helps make learning easier.

Improved robust regression with clean covariates achieves better rates than Huber's model.

Proposes LRR and LRLR for improving stock prediction accuracy.

Lower bound shows super-polynomial gap for estimating truncated Gaussian means.

Efficiently estimates prediction error in regression with Gaussian covariates under privacy constraints.

Active learning selects high-quality examples for text-to-SQL systems.

Prediction in a small-sized sample with a large number of covariates, the "small n, large p" problem, is challenging. This setting is encountered in multiple applications, such as precision medicine, where obtaining additional samples can be extremely costly or even impossible, and extensive research effort has recentl…

Solves TOD systems' query annotation problem without explicit annotations.

Study shows inefficiency of sparse linear regression learning with fewer than Ω(k^2) samples.

Study shows efficient algorithms for noiseless linear regression require quadratic sample complexity in contamination rate.

Study exact community recovery in noisy SBM with limited queries.

We study the problem of high-dimensional sparse mean estimation in the presence of an $ε$-fraction of adversarial outliers. Prior work obtained sample and computationally efficient algorithms for this task for identity-covariance subgaussian distributions. In this work, we develop the first efficient algorithms for rob…

The paper proposes a method to analyze categorical feature interactions in large datasets using graph covariance and LLMs.

Proposes a new query autocompletion method that maximizes retrieval performance.

LAZO reduces query complexity and variance in ZO methods.

We consider a query-based data acquisition problem for binary classification of unknown labels, which has diverse applications in communications, crowdsourcing, recommender systems and active learning. To ensure reliable recovery of unknown labels with as few number of queries as possible, we consider an effective quer…

We consider the problem of adaptively PAC-learning a probability distribution $\mathcal{P}$'s mode by querying an oracle for information about a sequence of i.i.d. samples $X_1, X_2, \ldots$ generated from $\mathcal{P}$. We consider two different query models: (a) each query is an index $i$ for which the oracle reveals…

Estimates heavy hitters in data streams with queries, balancing accuracy and efficiency.

Survey of statistical queries and their applications.

We study the query complexity of a learner-private sequential learning problem, motivated by the privacy and security concerns due to eavesdropping that arise in practical applications such as pricing and Federated Learning. A learner tries to estimate an unknown scalar value, by sequentially querying an external datab…

Source coding is the canonical problem of data compression in information theory. In a locally encodable source coding, each compressed bit depends on only few bits of the input. In this paper, we show that a recently popular model of semi-supervised clustering is equivalent to locally encodable source coding. In this …

A new query embedding method improves KB performance on complex queries.

Answering complex logical queries on large-scale incomplete knowledge graphs (KGs) is a fundamental yet challenging task. Recently, a promising approach to this problem has been to embed KG entities as well as the query into a vector space such that entities that answer the query are embedded close to the query. Howeve…

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^…

We study black-box attacks on machine learning classifiers where each query to the model incurs some cost or risk of detection to the adversary. We focus explicitly on minimizing the number of queries as a major objective. Specifically, we consider the problem of attacking machine learning classifiers subject to a budg…