arXiv research

New attacks reduce bad queries in black-box classifiers, improving effectiveness.

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…

Optimizes query routing to LLMs under cost and resource constraints.

Optimizes state monitoring in Markovian systems with cost constraints.

In query learning, the goal is to identify an unknown object while minimizing the number of "yes" or "no" questions (queries) posed about that object. A well-studied algorithm for query learning is known as generalized binary search (GBS). We show that GBS is a greedy algorithm to optimize the expected number of querie…

Budgeted deferral framework reduces expert query costs in machine learning.

ARL uses queries to learn rewards, focusing on cost vs. reward value.

Optimal DP mechanisms for vector queries are found to be staircase distributions.

Optimizes black-box functions with varying costs across multiple sources.

Survey on AL strategies for cost-effective annotation in classification.

Active learning method reduces label queries for positive examples.

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…

New algorithm reduces online hyperparameter optimization costs.

CARROT optimizes LLM routing by choosing the cheapest and most accurate model.

We consider the problem of prediction by a machine learning algorithm, called learner, within an adversarial learning setting. The learner's task is to correctly predict the class of data passed to it as a query. However, along with queries containing clean data, the learner could also receive malicious or adversarial …

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

Study reduces memory needs for active learning with enriched queries.

Unified framework for deferring queries to top-k experts, improving accuracy-cost trade-offs.

Bayesian framework for online consensus prediction from expert feedback.

Online Active Learning (OAL) aims to manage unlabeled datastream by selectively querying the label of data. OAL is applicable to many real-world problems, such as anomaly detection in health-care and finance. In these problems, there are two key challenges: the query budget is often limited; the ratio between classes i…

BMBO-DARN optimizes expensive functions with varying fidelities.

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 …

Similarity search retrieves the nearest neighbors of a query vector from a dataset of high-dimensional vectors. As the size of the dataset grows, the cost of performing the distance computations needed to implement a query can become prohibitive. A method often used to reduce this computational cost is quantization of …

Typical amortized inference in variational autoencoders is specialized for a single probabilistic query. Here we propose an inference network architecture that generalizes to unseen probabilistic queries. Instead of an encoder-decoder pair, we can train a single inference network directly from data, using a cost functi…

Optimal query allocation improves extractive QA efficiency with LLMs.

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

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

We investigate how an adversary can optimally use its query budget for targeted evasion attacks against deep neural networks in a black-box setting. We formalize the problem setting and systematically evaluate what benefits the adversary can gain by using substitute models. We show that there is an exploration-exploita…

Noisy Max and Sparse Vector are selection algorithms for differential privacy and serve as building blocks for more complex algorithms. In this paper we show that both algorithms can release additional information for free (i.e., at no additional privacy cost). Noisy Max is used to return the approximate maximizer amon…

Paper develops active learning for clustering unknown pairwise similarities.

The excessively increased volume of data in modern data management systems demands an improved system performance, frequently provided by data distribution, system scalability and performance optimization techniques. Optimized horizontal data partitioning has a significant influence of distributed data management syste…

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

Solving for adversarial examples with projected gradient descent has been demonstrated to be highly effective in fooling the neural network based classifiers. However, in the black-box setting, the attacker is limited only to the query access to the network and solving for a successful adversarial example becomes much …

sGPO optimizes RLVR training by balancing inference FLOPs and training 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…

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

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…

This paper proposes an active metric learning method for clustering with pairwise constraints.

We design an active learning algorithm for cost-sensitive multiclass classification: problems where different errors have different costs. Our algorithm, COAL, makes predictions by regressing to each label's cost and predicting the smallest. On a new example, it uses a set of regressors that perform well on past data t…

Accelerates Bayesian optimization of function networks with partial evaluations.

Algorithms learn and test variable partitions in various groups and error metrics.

This paper optimizes caching and model multiplexing for large model inference.

Improved API to achieve optimal error bound and query complexity in local planning.

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

We consider the problem of approximate $K$-means clustering with outliers and side information provided by same-cluster queries and possibly noisy answers. Our solution shows that, under some mild assumptions on the smallest cluster size, one can obtain an $(1+ε)$-approximation for the optimal potential with probabilit…

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

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

Feature missing is a serious problem in many applications, which may lead to low quality of training data and further significantly degrade the learning performance. While feature acquisition usually involves special devices or complex process, it is expensive to acquire all feature values for the whole dataset. On the…