arXiv research

Unified tractability conditions for various compositional inference queries.

Variational Autoencoders (VAEs) are a popular generative model, but one in which conditional inference can be challenging. If the decomposition into query and evidence variables is fixed, conditional VAEs provide an attractive solution. To support arbitrary queries, one is generally reduced to Markov Chain Monte Carlo …

We model GitHub interactions as a temporal knowledge graph for software engineering questions.

UQE uses LLMs to analyze unstructured data efficiently.

CUBE explains models by balanced experiments and contrasts.

Efficiently classifies binary labels with XOR queries, even under noisy conditions.

C-IP improves LLMs' query selection for interactive tasks by estimating uncertainty robustly.

Paper tackles efficient HMM learning with conditional samples.

Efficient methods for answering complex probabilistic queries in sequential data.

New algorithms learn MNL weights efficiently for any slate size.

New privacy mechanism reduces error in query results.

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

We consider the problem of learning causal relationships from relational data. Existing approaches rely on queries to a relational conditional independence (RCI) oracle to establish and orient causal relations in such a setting. In practice, queries to a RCI oracle have to be replaced by reliable tests for RCI against …

Statistical query algorithms and low-degree tests are nearly equivalent in high-dimensional hypothesis testing.

Paper studies model stealing for low-rank language models.

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…

New sampling algorithm for non-log-concave distributions requires many queries.

We formalize the notion of nesting probabilistic programming queries and investigate the resulting statistical implications. We demonstrate that while query nesting allows the definition of models which could not otherwise be expressed, such as those involving agents reasoning about other agents, existing systems take …

Optimizes state monitoring in Markovian systems with cost constraints.

Spanning attack improves black-box attacks with unlabeled data.

New algorithm tackles dynamic query routing to multiple embedding models.

This paper investigates the problem of determining a binary-valued function through a sequence of strategically selected queries. The focus is an algorithm called Generalized Binary Search (GBS). GBS is a well-known greedy algorithm for determining a binary-valued function through a sequence of strategically selected q…

Unified framework for simulation-based inference learns a single model for multiple tasks.

New algorithms learn from comparisons to classify data robustly to noise.

Semi-supervised active clustering (SSAC) utilizes the knowledge of a domain expert to cluster data points by interactively making pairwise "same-cluster" queries. However, it is impractical to ask human oracles to answer every pairwise query. In this paper, we study the influence of allowing "not-sure" answers from a w…

Improved sampling from high-dimensional Gaussians using smoothed scores.

We provide a new theoretical analysis framework to investigate online gradient descent in the dynamic environment. Comparing with the previous work, the new framework recovers the state-of-the-art dynamic regret, but does not require extra gradient queries for every iteration. Specifically, when functions are $α$ stron…

In this paper, we provide a method to learn the directed structure of a Bayesian network using data. The data is accessed by making conditional probability queries to a black-box model. We introduce a notion of simplicity of representation of conditional probability tables for the nodes in the Bayesian network, that we…

New method uses low logit rank to simplify complex language models.

The article presents a method that improves the quality of classification of objects described by a combination of known and unknown features. The method is based on modernized Informational Neurobayesian Approach with consideration of unknown features. The proposed method was developed and trained on 1500 text queries…

Study exact community recovery in noisy SBM with limited queries.

Study finds a method to discover causal relationships that are invariant to marginal distributions.

We propose a framework for Semi-Supervised Active Clustering framework (SSAC), where the learner is allowed to interact with a domain expert, asking whether two given instances belong to the same cluster or not. We study the query and computational complexity of clustering in this framework. We consider a setting where…

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.

New method uses zeroth-order queries to approximate proximal sampling efficiently.

New algorithms recover clusters with minimal queries, connecting margins to recoverability.

Online active regression algorithms minimize label queries for efficient data regression.

Paper analyzes risk bounds for in-context learning in multiclass classification.

Scarcity of training data for task-oriented dialogue systems is a well known problem that is usually tackled with costly and time-consuming manual data annotation. An alternative solution is to rely on automatic text generation which, although less accurate than human supervision, has the advantage of being cheap and f…

Improves model classification accuracy in black-box settings.

Studying a softmax-attention model, we show that the learned query converges to the latent signal subspace spanned by the informative direction.

New lower bounds for sampling from log-concave distributions in higher dimensions.

NeuralCSA uses neural networks to analyze causal effects under unobserved confounding.

Understanding search queries is critical for shopping search engines to deliver a satisfying customer experience. Popular shopping search engines receive billions of unique queries yearly, each of which can depict any of hundreds of user preferences or intents. In order to get the right results to customers it must be …

Establishes upper bounds on generalization error in active learning.

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

In many networks, vertices have hidden attributes, or types, that are correlated with the networks topology. If the topology is known but these attributes are not, and if learning the attributes is costly, we need a method for choosing which vertex to query in order to learn as much as possible about the attributes of …