Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,695 papers · 148 categories

Trend · papers per month

24487296 · Jun 202019922001200920172026
48 results for logarithmic queries

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

problem Scalability issue in combinatorial semi-bandit problems due to high combinatorial optimization costs.
method Oracle-efficient frameworks that minimize oracle queries while maintaining tight regret guarantees.
result Achieved ildeO(T) ilde{O}(\sqrt{T}) regret with O(loglogT)O(\log\log T) oracle queries for worst-case linear rewards.

Learn low-degree functions with few random queries.

problem Learning low-degree functions from limited random queries.
method Learn bounded functions f:{1,1}no[1,1]f:\{-1,1\}^n o[-1,1] of degree at most dd with L2L_2-accuracy ε\varepsilon and confidence 1δ1-δ from log(fracnδ)εd1Cd3/2logd\log( frac{n}δ)\,\varepsilon^{-d-1} C^{d^{3/2}\sqrt{\log d}} random queries.
result Learn low-degree functions efficiently with logarithmic number of random queries.

Exact cluster recovery with same-cluster queries for arbitrary ellipsoidal clusters.

problem Recovering clusters from same-cluster queries in arbitrary ellipsoidal clusters.
method Relaxing spherical kk-means assumption to arbitrary ellipsoidal clusters, designing an algorithm with logarithmic query complexity.
result Exact recovery of clusters using O(k3lnklnn)O(k^3 \ln k \ln n) queries and ildeO(kn+k3) ilde{O}(kn + k^3) time.

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.

Improved sampling from high-dimensional Gaussians using smoothed scores.

problem Sampling from high-dimensional Gaussian distributions with gradient information.
method Using smoothed scores, which are gradients of the logarithms of Gaussian-convolved densities, to overcome approximation barriers.
result Improved sampling efficiency with a complexity of \(O\left(\left(\logκ+\log(e\sqrt d/δ_{ m TV}) ight)\log(e\sqrt d/δ_{ m TV}) ight)\) smoothed-score queries.

We study the sample complexity of private synthetic data generation over an unbounded sized class of statistical queries, and show that any class that is privately proper PAC learnable admits a private synthetic data generator (perhaps non-efficient). Previous work on synthetic data generators focused on the case that …

2019-02-09abs ↗pdf ↗

We study the problem of estimating a set of dd linear queries with respect to some unknown distribution p\mathbf{p} over a domain J=[J]\mathcal{J}=[J] based on a sensitive data set of nn individuals under the constraint of local differential privacy. This problem subsumes a wide range of estimation tasks, e.g., distrib…

2018-10-05abs ↗pdf ↗

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

problem Risk bounds for in-context learning in multiclass classification.
method Formalizes tasks as sequences of labeled examples and queries, estimates conditional class probabilities, establishes oracle inequality for KL divergence.
result ICL achieves minimax optimal rate for conditional probability estimation.

In the world of big data, large but costly to label datasets dominate many fields. Active learning, a semi-supervised alternative to the standard PAC-learning model, was introduced to explore whether adaptive labeling could learn concepts with exponentially fewer labeled samples. While previous results show that active…

2019-07-08abs ↗pdf ↗

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…

2017-09-11abs ↗pdf ↗

The paper establishes lower bounds for learning polynomial functions on hypercube.

problem Establishing lower bounds for learning polynomial functions on the discrete hypercube.
method Using packing numbers and Fourier analysis, the paper proves lower bounds on the number of queries needed for learning.
result Proves sharp lower bounds on the number of queries required for learning polynomial functions.

The study quantifies the information needed for causal queries at different levels of Pearl's hierarchy.

problem How much additional information is needed for interventional and counterfactual queries compared to observational queries?
method Formalized via query-class description length, using Kolmogorov complexity of answer oracles induced by SCMs.
result Binary acyclic SCMs show a quadratic gap between observational and interventional descriptions, and a logarithmic gap between interventional and counterfactual descriptions.

Suppose, we are given a set of nn elements to be clustered into kk (unknown) clusters, and an oracle/expert labeler that can interactively answer pair-wise queries of the form, "do two elements uu and vv belong to the same cluster?". The goal is to recover the optimum clustering by asking the minimum number of quer…

2017-06-23abs ↗pdf ↗

We consider the problem of optimizing a high-dimensional convex function using stochastic zeroth-order queries. Under sparsity assumptions on the gradients or function values, we present two algorithms: a successive component/feature selection algorithm and a noisy mirror descent algorithm using Lasso gradient estimate…

2017-10-29abs ↗pdf ↗

Study shows limitations and possibilities of learning quantum circuit output distributions.

problem Learnability of output distributions of local quantum circuits.
method Investigated within two oracle models: statistical query model and direct sample access model.
result Output distributions of super-logarithmic depth Clifford circuits are not efficiently learnable in the statistical query model.

Improves retrieval accuracy for hierarchical documents, especially for distant matches.

problem Limited expressive power of dual encoder models in hierarchical retrieval.
method Proves feasibility of DEs for HR, introduces pretrain-finetune recipe to improve long-distance retrieval.
result Pretrain-finetune boosts recall on long-distance pairs from 19% to 76%.

Optimistic search speeds up change point detection in large datasets.

problem Efficiently detecting change points in large-scale data with high computational demands.
method Adaptive logarithmic queries to reduce evaluation complexity.
result Asymptotic minimax optimality and fast localization rates for change point detection.

Paper addresses privacy and robustness in stochastic linear bandits.

problem Stochastic linear bandits with differential privacy and adversarial robustness.
method Logarithmic batch queries, arm elimination algorithm, two privacy models.
result First algorithms providing differential privacy and adversarial robustness.

Datasets are often reused to perform multiple statistical analyses in an adaptive way, in which each analysis may depend on the outcomes of previous analyses on the same dataset. Standard statistical guarantees do not account for these dependencies and little is known about how to provably avoid overfitting and false d…

2017-06-15abs ↗pdf ↗

We study online active learning for classifying streaming instances within the framework of statistical learning theory. At each time, the learner either queries the label of the current instance or predicts the label based on past seen examples. The objective is to minimize the number of queries while constraining the…

2019-04-19abs ↗pdf ↗

We give algorithms for estimating the expectation of a given real-valued function φ:XRφ:X\to {\bf R} on a sample drawn randomly from some unknown distribution DD over domain XX, namely ExD[φ(x)]{\bf E}_{{\bf x}\sim D}[φ({\bf x})]. Our algorithms work in two well-studied models of restricted access to data samples. The first o…

2016-11-20abs ↗pdf ↗

Many machine learning models can be attacked with adversarial examples, i.e. inputs close to correctly classified examples that are classified incorrectly. However, most research on adversarial attacks to date is limited to vectorial data, in particular image data. In this contribution, we extend the field by introduci…

2019-08-25abs ↗pdf ↗

We design and study a Contextual Memory Tree (CMT), a learning memory controller that inserts new memories into an experience store of unbounded size. It is designed to efficiently query for memories from that store, supporting logarithmic time insertion and retrieval operations. Hence CMT can be integrated into existi…

2018-07-17abs ↗pdf ↗

New algorithms sample structured logconcave families with improved efficiency.

problem Sampling structured logconcave families to high accuracy.
method Reduction framework inspired by proximal point methods, combined with restricted Gaussian oracles.
result Improved bounds for sampling structured distributions, matching or surpassing state-of-the-art results.

In the era of big data, learning from categorical features with very large vocabularies (e.g., 28 million for the Criteo click prediction dataset) has become a practical challenge for machine learning researchers and practitioners. We design a highly-scalable vocabulary compression algorithm that seeks to maximize the …

2019-04-30abs ↗pdf ↗

Optimizes private learning with differential privacy for LASSO problems.

problem Private optimization of convex functions over 1\ell_1-bounded domains.
method Combines iterative localization with private regularized mirror descent and variance-reduced Frank-Wolfe algorithm.
result Achieves optimal excess population loss rates in 1\ell_1 geometry.

Proposes a new query autocompletion method that maximizes retrieval performance.

problem Users often select suboptimal queries due to unknown best retrieval performance.
method Formulates query autocompletion as ranking item rankings, uses counterfactual learning.
result Empirical results show improved query suggestions for better retrieval performance.

New lower bounds show learning intersections of halfspaces is hard even for a few halfspaces.

problem Learning intersections of halfspaces in polynomial time under standard assumptions.
method Unified connection to parallel pancakes distribution for proving hardness.
result Learning ω(loglogN)ω(\log \log N) halfspaces in dimension NN requires super-polynomial time under standard assumptions.

We consider the problem of strongly-convex online optimization in presence of adversarial delays; in a T-iteration online game, the feedback of the player's query at time t is arbitrarily delayed by an adversary for d_t rounds and delivered before the game ends, at iteration t+d_t-1. Specifically for \algo{online-gradi…

2016-05-20abs ↗pdf ↗

We consider the problem of adaptively PAC-learning a probability distribution P\mathcal{P}'s mode by querying an oracle for information about a sequence of i.i.d. samples X1,X2,X_1, X_2, \ldots generated from P\mathcal{P}. We consider two different query models: (a) each query is an index ii for which the oracle reveals…

2019-11-19abs ↗pdf ↗

Query2box embeds complex queries as boxes to handle logical operations in large KGs.

problem Handling complex logical queries on large-scale incomplete knowledge graphs.
method Embed KG entities and queries into a vector space as boxes, handling conjunctions as intersections and disjunctions through Disjunctive Normal Form.
result Query2box achieves up to 25% relative improvement over state-of-the-art methods.