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.

168,742 papers · 148 categories

Trend · papers per month

2625247861,048 · Jun 202019922001200920172026
48 results for linear hypothesis sets

Analyzes the complexity of linear hypothesis sets using Rademacher complexity.

problem Understanding the complexity of linear hypothesis sets for various norms.
method Tight analysis of empirical Rademacher complexity for linear hypothesis classes with bounded weights.
result Improved bounds on Rademacher complexity for linear hypothesis sets, matching or improving existing results.

New algorithm selects best distribution privately in nearly-linear time.

problem Estimating the best distribution from samples under differential privacy constraints.
method Differentially private algorithm with nearly-linear time complexity and optimal approximation factor.
result Achieves optimal approximation factor of 3 with modest sample complexity increase.

New algorithms for model selection in linear bandits adapt to instance complexity.

problem Adapting to the instance-dependent complexity of the true model in linear bandits.
method Design of algorithms in fixed confidence and fixed budget settings, leveraging experimental design and selection-validation procedures.
result Near instance optimal guarantees for model selection in linear bandits.

This paper reviews the functional aspects of statistical learning theory. The main point under consideration is the nature of the hypothesis set when no prior information is available but data. Within this framework we first discuss about the hypothesis set: it is a vectorial space, it is a set of pointwise defined fun…

2009-10-06abs ↗pdf ↗

We propose a methodology for testing linear hypothesis in high-dimensional linear models. The proposed test does not impose any restriction on the size of the model, i.e. model sparsity or the loading vector representing the hypothesis. Providing asymptotically valid methods for testing general linear functions of the …

2016-10-10abs ↗pdf ↗

Study on calibration and consistency of adversarial surrogate losses.

problem Designing robust classifiers with theoretical guarantees.
method Extensive analysis of H-calibration and H-consistency of adversarial surrogate losses.
result Some convex loss functions and supremum-based convex losses are not H-calibrated for important hypothesis sets.

The paper defines a hypothesis space for deep learning using DNNs.

problem Developing a mathematical framework for deep learning.
method Introducing a Banach space of functions of input variables based on DNNs, proving it's a RKBS, and establishing representer theorems for learning models.
result Solutions to learning problems can be expressed as finite sums of kernel expansions based on training data.

In this paper we address the problem of pool based active learning, and provide an algorithm, called UPAL, that works by minimizing the unbiased estimator of the risk of a hypothesis in a given hypothesis space. For the space of linear classifiers and the squared loss we show that UPAL is equivalent to an exponentially…

2011-11-08abs ↗pdf ↗

Proposes a new approach to regression learning that addresses overfitting and underfitting.

problem Regression learning issues, including overfitting and underfitting.
method Introduces epsilon-Confidence Approximately Correct (epsilon CoAC) framework using Kullback Leibler divergence.
result Demonstrates improved learnability and accuracy compared to cross-validation.

Compact solutions persist even with linear perturbations of the mean curvature term.

problem Compactness of solutions to the Yamabe problem on manifolds with boundary.
method Linear perturbation of the mean curvature term, proving compactness of solutions.
result Set of solutions remains compact even with negative perturbations.

Study improves hypothesis transfer learning for functional linear models.

problem Incompatible TL techniques for high-dimensional FLR methods due to infinite-dimensional nature of functional data.
method Proposes two algorithms for hypothesis transfer learning in RKHS framework, leveraging RKHS distance and aggregation techniques.
result Establishes asymptotic lower bounds and matching upper bounds for the proposed algorithms, demonstrating their effectiveness.

We present a study of generalization for data-dependent hypothesis sets. We give a general learning guarantee for data-dependent hypothesis sets based on a notion of transductive Rademacher complexity. Our main result is a generalization bound for data-dependent hypothesis sets expressed in terms of a notion of hypothe…

2019-04-09abs ↗pdf ↗

The study sets lower bounds on MMSE for inferring sensitive features from noisy data.

problem Estimating sensitive features from noisy observations of correlated features.
method Adversarial evaluation framework based on MMSE estimation with theoretical lower bounds.
result Derives closed-form bounds for linear models, showing optimality in noise variance.

Unified framework for large-scale hypothesis testing with confounders.

problem Bias in large-scale hypothesis testing due to unmeasured confounders.
method Unified statistical estimation and inference framework that disentangles confounding effects and jointly estimates latent and primary effects.
result Effective Type-I error control and power in hypothesis testing.

This paper proves the manifold hypothesis for lower embedding dimensions using osculating hyperspheres.

problem The dataset lies on a low-dimensional submanifold in high-dimensional space.
method Constructing osculating hyperspheres and applying surgery theory to embed the hypersurface.
result The manifold hypothesis holds for embedding dimensionalities up to d1d-1.

Develops a framework to test excessive influence of small data subsets.

problem Identifying when small data subsets significantly impact model conclusions.
method Formalizes the concept of most influential sets, deriving influence formulas and extreme value distributions.
result Allows rigorous hypothesis testing for excessive influence, resolving contested findings.

We study whether a neural network optimizes to the same, linearly connected minimum under different samples of SGD noise (e.g., random data order and augmentation). We find that standard vision models become stable to SGD noise in this way early in training. From then on, the outcome of optimization is determined to a …

2019-12-11abs ↗pdf ↗

Efficient tests achieve best error rates in high-dimensional hypothesis testing.

problem Achieving optimal error rates in computationally efficient hypothesis testing.
method Linear spectral statistics and low-degree likelihood ratio analysis.
result An efficient test achieves the best possible error rates among all computationally efficient tests.

This letter presents a novel Block Bayesian Hypothesis Testing Algorithm (Block-BHTA) for reconstructing block sparse signals with unknown block structures. The Block-BHTA comprises the detection and recovery of the supports, and the estimation of the amplitudes of the block sparse signal. The support detection and rec…

2015-08-22abs ↗pdf ↗

Comparative learning combines realizable and agnostic settings for two hypothesis classes, reducing sample complexity.

problem Learning with two hypothesis classes in a more general setting than single hypothesis classes.
method Introduces comparative learning, defines mutual VC dimension and Littlestone dimension, and applies insights to multiaccuracy and multicalibration.
result Sample complexity of comparative learning is characterized by mutual VC dimension and Littlestone dimension.

Extends linear representation hypothesis to categorical and hierarchical concepts in LLMs.

problem Representing concepts without natural contrasts in large language models.
method Formalizes linear representation hypothesis for categorical and hierarchical concepts, proving relationships between concept hierarchy and representation geometry.
result Validated theoretical results on large language models, estimating representations for 900+ concepts.

We formulate statistical watermarking as hypothesis testing and establish near-optimal bounds.

problem Statistical watermarking in the context of hypothesis testing.
method Formulated as a hypothesis testing problem, using coupling of output tokens and rejection regions.
result Established nearly matching upper and lower bounds on the number of i.i.d. tokens required for small Type I and Type II errors.

New study shows neural networks can generalize without gradient descent, especially in deep settings.

problem Whether neural networks need gradient descent for generalization.
method Theoretical study of matrix factorization with linear and non-linear activation, comparing gradient descent to Guess & Check.
result Generalization under Guess & Check deteriorates with increasing width but improves with depth, challenging conventional wisdom.

Formula derived for sample complexity in binary hypothesis testing.

problem Determine the minimum number of samples to distinguish between two distributions.
method Developed a formula for sample complexity in both prior-free and Bayesian settings, using Jensen-Shannon and Hellinger divergences.
result Formula characterizes sample complexity for a wide range of error parameters, up to multiplicative constants.

Lower bounds and upper bounds on sample complexity for identifying linear dynamical systems.

problem Identifying an unknown linear dynamical system with limited data.
method Sample complexity lower and upper bounds, persistent excitation condition, active learning algorithm.
result Lower and upper bounds share the same dependency on key problem parameters.

Paper studies PSGD for constrained optimization problems and its statistical properties.

problem Online inference for constrained optimization problems.
method Stochastic gradient descent with projection (PSGD) for constrained optimization.
result Limiting distribution of PSGD-based estimates under linear-equality constraints.

Binary testing for softmax models requires many samples, similar to leverage score models.

problem Binary hypothesis testing for softmax models and leverage score models.
method Analyzing sample complexity and drawing analogies between models.
result Sample complexity is asymptotically \(O(ε^{-2})\), where \(ε\) is the distance between model parameters.

The two-sample hypothesis testing problem is studied for the challenging scenario of high dimensional data sets with small sample sizes. We show that the two-sample hypothesis testing problem can be posed as a one-class set classification problem. In the set classification problem the goal is to classify a set of data …

2017-06-18abs ↗pdf ↗

Optimal subset selection for hypothesis testing with penalties.

problem Optimal subset selection of information sources for hypothesis testing with misclassification penalties.
method Proposes a misclassification penalty framework and studies two variants of subset selection problems under centralized Bayesian learning.
result Proves the submodularity of the objective and constraints of the subset selection problems and establishes performance guarantees for greedy algorithms.

Suppose some classifiers are selected from a set of hypothesis classifiers to form an equally-weighted ensemble that selects a member classifier at random for each input example. Then the ensemble has an error bound consisting of the average error bound for the member classifiers, a term for selectivity that varies fro…

2016-10-04abs ↗pdf ↗

Paper extends Chernoff sampling for active testing and parameter estimation, improving neural network and regression models.

problem Reducing sample complexity in hypothesis testing and model parameter estimation.
method Developed an extension of Chernoff sampling for active learning and parameter estimation.
result Non-asymptotic bounds for sample complexity and estimation error in active learning.

Paper tackles hypothesis transfer learning for black-box models.

problem Difficult to build universal machine learning models across different institutions.
method Dynamic Knowledge Distillation (dkdHTL) with instance-wise weighting.
result Empirical results show the effectiveness of dkdHTL.