Learn low-degree functions with few random queries.
problem Learning low-degree functions from limited random queries.
method Learn bounded functions f : { − 1 , 1 } n o [ − 1 , 1 ] f:\{-1,1\}^n o[-1,1] f : { − 1 , 1 } n o [ − 1 , 1 ] of degree at most d d d with L 2 L_2 L 2 -accuracy ε \varepsilon ε and confidence 1 − δ 1-δ 1 − δ from log ( f r a c n δ ) ε − d − 1 C d 3 / 2 log d \log( frac{n}δ)\,\varepsilon^{-d-1} C^{d^{3/2}\sqrt{\log d}} log ( f r a c n δ ) ε − d − 1 C d 3/2 l o g d random queries. result Learn low-degree functions efficiently with logarithmic number of random queries.
Paper reveals free information from differential privacy mechanisms improving query accuracy.
problem Improving query accuracy with differential privacy mechanisms.
method Analysis of Noisy Max and Sparse Vector mechanisms.
result Noisy Max releases the noisy gap between the approximate maximizer and runner-up.
Adaptive Misinformation defends against model stealing attacks by sending incorrect predictions for OOD queries.
problem Model stealing attacks clone target models using black-box query access and a surrogate dataset.
method Selective sending of incorrect predictions for Out-Of-Distribution (OOD) queries to degrade attacker's clone model accuracy.
result Our defense reduces attacker's clone model accuracy by up to 40% while maintaining benign user accuracy under 0.5%.
We consider accurately answering smooth queries while preserving differential privacy. A query is said to be K K K -smooth if it is specified by a function defined on [ − 1 , 1 ] d [-1,1]^d [ − 1 , 1 ] d whose partial derivatives up to order K K K are all bounded. We develop an ε ε ε -differentially private mechanism for the class of K K K -smooth queries…
This work sets lower bounds on the number of score queries needed for diffusion sampling.
problem Establishing information-theoretic limits on the number of score evaluations required for diffusion sampling.
method Proving lower bounds on the number of adaptive score queries needed for sampling.
result Any sampling algorithm requires at least \(\widetilde{\Omega}(\sqrt{d})\) adaptive score queries for \(d\)-dimensional distributions.
Marich extracts high-fidelity models from public data with minimal queries.
problem Creating an accurate replica of a target ML model using few queries.
method Sequentially selects informative queries to maximize entropy and reduce model mismatch.
result Extracted models achieve 60-95% of target model's accuracy with 1,000-8,500 queries.
Efficiently classifies binary labels with XOR queries, even under noisy conditions.
problem Binary classification with unknown labels using XOR queries.
method Effective query type and an efficient inference algorithm for noisy conditions.
result Achieves information-theoretic limit on optimal number of queries.
StreamEnsemble dynamically selects ML models for ST data streams to improve predictive accuracy.
problem Predictive queries over spatiotemporal data streams are challenging due to varying distributions and patterns.
method Dynamic selection and allocation of ML models based on time series distributions and characteristics.
result Significantly outperforms traditional ensemble and single model approaches, reducing prediction error by over 10 times.
Assessing the predictive accuracy of black box classifiers is challenging in the absence of labeled test datasets. In these scenarios we may need to rely on a human oracle to evaluate individual predictions; presenting the challenge to create query algorithms to guide the search for points that provide the most informa…
Budgeted deferral framework reduces expert query costs in machine learning.
problem High cost of querying all experts in deferral algorithms.
method Introduces budgeted deferral framework for selective expert querying.
result Empirical results show substantial reduction in training costs without sacrificing accuracy.
Active learning optimizes correlation clustering by querying the most informative pairwise comparisons.
problem Efficiently clustering data with limited pairwise similarity information.
method Developed principled active learning approach using information-theoretic acquisition functions.
result Significantly outperforms existing baselines in clustering accuracy and query efficiency.
LEAQI learns to query an expert less often for noisy guidance.
problem Active imitation learning with noisy guidance to reduce expert query complexity.
method Developed LEAQI, a difference classifier that predicts expert disagreement with noisy heuristic.
result Significantly fewer queries to the expert with comparable or better accuracy.
We formulate a private learning model to study an intrinsic tradeoff between privacy and query complexity in sequential learning. Our model involves a learner who aims to determine a scalar value, v ∗ v^* v ∗ , by sequentially querying an external database and receiving binary responses. In the meantime, an adversary observes…
AdvMind detects adversary intent in black-box attacks with high accuracy.
problem Detecting adversary intent in black-box adversarial attacks is challenging.
method AdvMind accounts for adversary adaptiveness and synthesizes queries to expose intent.
result AdvMind detects adversary intent with over 75% accuracy after observing less than 3 query batches.
Improves model classification accuracy in black-box settings.
problem Difficulty in inferring model properties due to limited query access.
method Introduces discriminative factorization to distinguish high-quality queries.
result Probability of chance-level classification decreases exponentially with query budget.
ALPINE predicts links in networks by querying the most informative pairs.
problem Predicting links in partially observed networks efficiently.
method Active learning using network embedding.
result ALPINE achieves significant link prediction accuracy with fewer queries.
SOLAR improves search efficiency and accuracy with sparse, orthogonal embeddings.
problem Bottleneck of indexing large dense vectors and NNS for query efficiency and accuracy.
method Proposes SOLAR embeddings: sparse, orthogonal, learned, and random vectors across multiple GPUs.
result Successfully trains 500K dimensional SOLAR embeddings for 1.6M books and multi-label classification.
Estimates heavy hitters in data streams with queries, balancing accuracy and efficiency.
problem Identifying elements with high probability in i.i.d. samples.
method Sequential estimation algorithms for two query models: index and pair queries.
result Upper and lower bounds on query complexity for different distributions and noise models.
Study optimizes query strategy for private learning in eavesdropping scenarios.
problem Private sequential learning in the presence of eavesdropping.
method Developed new querying strategies and analytical techniques.
result Proved tight upper and lower bounds on optimal query complexity.
Discrete Gaussian noise preserves privacy and accuracy in differential privacy.
problem Finite computers cannot represent continuous Gaussian noise, leading to privacy breaches and loss of interpretability.
method Introduced and analyzed discrete Gaussian noise, providing privacy and accuracy guarantees similar to continuous Gaussian noise.
result Discrete Gaussian noise offers the same privacy and accuracy as continuous Gaussian noise, with efficient sampling algorithms.
Adaptive compute allocation improves model performance by prioritizing harder queries.
problem Inefficiency in allocating test-time compute uniformly across all queries.
method Formulated as a bandit learning problem, proposed adaptive algorithms that estimate query difficulty and allocate compute accordingly.
result Achieved up to 15.29% relative performance improvement on various benchmarks.
Three new oracle-efficient algorithms for private synthetic data release.
problem Constructing private synthetic data that preserves statistical query answers.
method Oracle-efficient algorithms using optimization oracles for differential privacy.
result Better accuracy in large workload and high privacy regime compared to state-of-the-art.
The paper bridges theory and practice in query-driven selectivity learning.
problem Insufficient theoretical understanding of query-driven selectivity learning.
method Demonstrates learnability of selectivity predictors and establishes favorable OOD generalization error bounds.
result Theoretical advances improve OOD generalization of query-driven selectivity models.
QActor optimizes learning from noisy labeled data streams by querying experts for clean labels.
problem Learning from noisy labeled data in continuous streams with limited oracle queries.
method Combines quality models for filtering and oracle queries for true labels, dynamically adjusting query limits.
result QActor nearly matches optimal accuracy with up to 6% additional ground truth data from experts.
Quadratic memory is essential for optimal convex optimization queries.
problem Optimal query complexity for convex optimization and feasibility problems.
method Lower bounds on query complexity for convex optimization and feasibility problems.
result Center-of-mass algorithms are Pareto-optimal for both convex optimization and feasibility problems.
Optimizes state monitoring in Markovian systems with cost constraints.
problem Balancing state queries with prediction costs in Markovian systems.
method Greedy policy and SGD-based learning variant for optimal predict-query tradeoff.
result Greedy policy is suboptimal but performs close to optimal under certain conditions.
Unified framework for deferring queries to top-k experts, improving accuracy-cost trade-offs.
problem Limitation of existing L2D frameworks to single-expert deferral.
method Top- k k k Learning-to-Defer framework, including adaptive Top- k ( x ) k(x) k ( x ) variant. result Superior accuracy-cost trade-offs with multi-expert deferral.
Path queries on a knowledge graph can be used to answer compositional questions such as "What languages are spoken by people living in Lisbon?". However, knowledge graphs often have missing facts (edges) which disrupts path queries. Recent models for knowledge base completion impute missing facts by embedding knowledge…
Optimizes query routing to LLMs under cost and resource constraints.
problem Non-uniform or adversarial batching in per-query routing methods leads to cost inefficiency.
method Batch-level, resource-aware routing framework that jointly optimizes model assignment for each batch.
result Robust routing framework improves accuracy by 1-14% over non-robust methods.
New bounds show complex neural networks need many queries to learn.
problem Learning non-polynomial activation functions with Gaussian marginals.
method Gradient boosting procedure to amplify lower bounds on SQ dimension of neural networks.
result Statistical-query lower bounds for ReLU regression with 2 n c ε 2^{n^c} ε 2 n c ε queries. This work proposes a collaborative multi-head attention layer to reduce model size without sacrificing accuracy.
problem Over-parameterization in transformer models trained with large datasets.
method Proposes a collaborative multi-head attention layer that shares key/query projections.
result Reduction in model size by 4 for same accuracy and speed.
Crowdsourced labeling recovers task types with minimal queries.
problem Labeling tasks accurately with minimal queries.
method Worker clustering, skill estimation, weighted majority voting.
result Achieves any targeted recovery accuracy with minimum queries.
Paper studies how incomplete data affects machine learning, proposing 'Certain Predictions' for NN classifiers.
problem Impact of incomplete and inconsistent data on machine learning applications.
method Extends Certain Answers concept to machine learning, introduces 'Certain Predictions' for NN classifiers.
result Developed efficient solutions for CP queries in NN classifiers, improving classification accuracy.
Paper uses deep learning for accurate, monotonic cardinality estimation.
problem Accurate and monotonic cardinality estimation for similarity selection.
method Feature extraction to Hamming space, followed by deep learning regression.
result Demonstrates improved query optimizer performance.
FAQ efficiently evaluates LLMs with statistical guarantees using adaptive query selection.
problem Efficiently evaluating many LLMs on a large suite of benchmarks is expensive.
method FAQ uses Bayesian factor models, adaptive sampling, and proactive active inference to select queries.
result FAQ delivers up to 5x effective sample size gains over baselines, matching CI width with fewer queries.
RayS attack improves hard-label adversarial attacks by reducing query complexity and identifying false robust models.
problem Challenges in hard-label adversarial attacks, especially in terms of effectiveness and efficiency.
method Reformulates continuous problem into discrete problem without gradient estimation and uses a fast check step to eliminate unnecessary searches.
result Significantly reduces the number of queries needed for hard-label attacks and identifies false robust models.
New method tackles geodesically convex optimization with polynomial convergence.
problem Designing an efficient algorithm for geodesically convex optimization.
method Ellipsoid-like algorithm with polynomial query and per-query complexity.
result Achieves polynomial convergence for geodesically convex functions.
New stability notion ensures generalization in adaptive settings for linear queries.
problem Ensuring generalization in adaptive settings for linear queries.
method Introducing a new stability notion based on observing outputs and quantifying their effect on posterior data sample elements.
result The new stability notion is both necessary and sufficient for generalization in adaptive settings.
New method generates private synthetic data with optimal utility for smooth queries.
problem Achieving strong utility guarantees for meaningful downstream analysis of sensitive datasets.
method Proposes a polynomial-time algorithm for generating ( ε , δ ) (\varepsilon,δ) ( ε , δ ) -differentially private synthetic data with minimax optimal error rates for smooth queries. result Achieves a minimax error rate of O k , d ( n − min { 1 , k d } ) O_{k,d}(n^{-\min \{1, \frac{k}{d}\}}) O k , d ( n − m i n { 1 , d k } ) for k k k -smooth queries, up to a log ( n ) \log(n) log ( n ) factor. Fuzzy clustering with similarity queries improves efficiency and accuracy.
problem Clustering uncertain or vague datasets.
method Semi-supervised active clustering framework with oracle similarity queries.
result Polynomial-time approximation algorithm for fuzzy clustering with few similarity queries.
Memory-constrained algorithms need superlinear memory for efficient convex optimization.
problem Efficiently minimizing convex functions with limited memory.
method Analyzing first-order algorithms with superlinear memory constraints.
result Superlinear memory is necessary for optimal performance in convex optimization.
Adapts data analysis for growing data, improving generalization guarantees.
problem Challenges of overfitting and statistical validity in adaptive workflows with growing data.
method Generalizes adaptive analysis on dynamic data, incorporating time-varying empirical accuracy bounds and mechanisms.
result First generalization bounds for adaptive analysis on dynamic data, matching prior works' improvement over data splitting.
Active learning aims to obtain a classifier of high accuracy by using fewer label requests in comparison to passive learning by selecting effective queries. Many active learning methods have been developed in the past two decades, which sample queries based on informativeness or representativeness of unlabeled data poi…
Ricci-Filtration enhances retrieval-augmented generation rerankers for query-answer tasks by using discrete Ricci flow on graphs.
problem Improving retrieval-augmented generation rerankers for query-answer tasks.
method Discrete Ricci flow on graphs to evaluate structural importance of chunks.
result Ricci-Filtration outperforms baseline methods in accuracy, precision, recall, and F1 scores.
Improved private sample complexity for answering classification queries.
problem Designing an algorithm to accurately answer classification queries while maintaining differential privacy.
method Formally studied in agnostic PAC model, derived new upper bound on private sample complexity.
result Improved private sample complexity bound for answering classification queries.
Machine learning models are vulnerable to simple model stealing attacks if the adversary can obtain output labels for chosen inputs. To protect against these attacks, it has been proposed to limit the information provided to the adversary by omitting probability scores, significantly impacting the utility of the provid…
New algorithms reduce overfitting in multiclass classification.
problem Excessive reuse of test datasets in machine learning leads to overfitting, especially in multiclass classification.
method Developed computationally efficient algorithms to reduce overfitting bias in multi-class classification.
result Achieved overfitting bias of Θ(√(k/(mn)), k/n), matching known upper bounds.
The use of community detection algorithms is explored within the framework of cover song identification, i.e. the automatic detection of different audio renditions of the same underlying musical piece. Until now, this task has been posed as a typical query-by-example task, where one submits a query song and the system …