arXiv research

Study examines how uncertainty visualization affects analyst trust in automated classification systems.

A quantum reinforcement learning algorithm reduces sample complexity.

RPI combines imitation and reinforcement learning to improve policies efficiently.

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.

We study the problem of interactively learning a binary classifier using noisy labeling and pairwise comparison oracles, where the comparison oracle answers which one in the given two instances is more likely to be positive. Learning from such oracles has multiple applications where obtaining direct labels is harder bu…

Pairwise "same-cluster" queries are one of the most widely used forms of supervision in semi-supervised clustering. However, it is impractical to ask human oracles to answer every query correctly. In this paper, we study the influence of allowing "not-sure" answers from a weak oracle and propose an effective algorithm …

We define and study the problem of modular concept learning, that is, learning a concept that is a cross product of component concepts. If an element's membership in a concept depends solely on it's membership in the components, learning the concept as a whole can be reduced to learning the components. We analyze this …

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

New algorithm for clustering with faulty oracle achieves optimal queries and efficiency.

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…

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…

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

New RLHF framework handles general preference oracles without reward functions.

Algorithm identifies nearest mode in noisy data.

Gradient descent is efficient for solving feasibility problems with minimal memory and queries.

Optimizes reward learning design for complex tasks using nonparametric methods.

Quantum algorithms for multi-armed bandits are explored with limited reward access.

Study exact community recovery in noisy SBM with limited queries.

New algorithm finds k-centers from noisy distance estimates.

New method recovers clusters in non-convex finite metric spaces with oracle queries.

Efficient algorithms recover two sparse models from a mix of linear queries.

Three new oracle-efficient algorithms for private synthetic data release.

MAMBA learns policies competitive with multiple conflicting oracles.

Study on tradeoffs between mistakes and ERM oracle calls in online and transductive learning.

Unified approach for quantum and classical learning from evaluation oracles.

Interactive IL algorithm queries noisy expert for feedback, reducing sample size.

New tool for parallel and private stochastic convex optimization reduces query complexity.

Many machine learning tasks such as clustering, classification, and dataset search benefit from embedding data points in a space where distances reflect notions of relative similarity as perceived by humans. A common way to construct such an embedding is to request triplet similarity queries to an oracle, comparing two…

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

There is increasing interest in learning algorithms that involve interaction between human and machine. Comparison-based queries are among the most natural ways to get feedback from humans. A challenge in designing comparison-based interactive learning algorithms is coping with noisy answers. The most common fix is to …

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 …

Efficiently clusters noisy data with minimal queries.

New protocol identifies impossible edge orientations in causal graphs.

MAPS and MAPS-SE learn from multiple suboptimal experts to improve policies efficiently.

New oracle uses uncertainty for active classification with noisy feedback.

Noisy labeled data is more a norm than a rarity for self-generated content that is continuously published on the web and social media. Due to privacy concerns and governmental regulations, such a data stream can only be stored and used for learning purposes in a limited duration. To overcome the noise in this on-line s…

Quadratic memory is essential for optimal convex optimization queries.

GPE algorithm optimizes nonparametric contextual bandits with efficient regret bounds.

Quantum oracles help identify counterfactuals better than classical ones.

Optimizes state monitoring in Markovian systems with cost constraints.

A generative model may generate utter nonsense when it is fit to maximize the likelihood of observed data. This happens due to "model error," i.e., when the true data generating distribution does not fit within the class of generative models being learned. To address this, we propose a model of active distribution lear…

Algorithm samples composite logconcave densities efficiently.

Oracle-efficient algorithm for offline RL with partial data coverage.

Bayesian optimization improves policy search in reinforcement learning.

Paper addresses online alignment of large language models under uncertain preference feedback.

We note that known methods achieving the optimal oracle complexity for first order convex optimization require quadratic memory, and ask whether this is necessary, and more broadly seek to characterize the minimax number of first order queries required to optimize a convex Lipschitz function subject to a memory constra…

Paper tackles noisy comparison oracle for robust clustering algorithms.