Selecting appropriate regularization coefficients is critical to performance with respect to regularized empirical risk minimization problems. Existing theoretical approaches attempt to determine the coefficients in order for regularized empirical objectives to be upper-bounds of true objectives, uniformly over a hypot…
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
48 results for “Generic Regularity Hypothesis”
Optimal systolic inequality proved for manifolds with positive bi-Ricci curvature.
problem Proving optimal systolic inequalities on manifolds with positive bi-Ricci curvature.
method Minimal surfaces method under the Generic Regularity Hypothesis.
result Optimal systolic inequality proved in all dimensions.
A typical approach in estimating the learning rate of a regularized learning scheme is to bound the approximation error by the sum of the sampling error, the hypothesis error and the regularization error. Using a reproducing kernel space that satisfies the linear representer theorem brings the advantage of discarding t…
We prove that the existence of regular Lagrangians can be given by existence of Weinstein Lefschetz fibrations with an hypothesis.
Entropy regularized OT test assesses independence between samples.
problem Testing independence between two samples.
method Entropy regularized optimal transport.
result Non-asymptotic bounds for test statistic established.
Unified theory for representation learning using learnable functions.
problem Insufficient theoretical understanding of unsupervised and self-supervised learning.
method Discriminative theoretical framework for analyzing sample complexity.
result Learnable regularization functions can reduce the amount of labeled data needed.
Establishes upper bounds on generalization error in active learning.
problem Improving query algorithms in active learning.
method Derives upper bounds on generalization error using informativeness and representativeness query strategies.
result Validates the use of regularization techniques to ensure bounds' validity.
Estimates neural network errors for classification problems.
problem Binary and multi-class classification problems.
method Rademacher complexity estimates and direct approximation theorems.
result A priori error estimates for regularized loss functionals.
Universal Inferencemath.ST
A universal method for hypothesis tests and confidence sets without regularity conditions.
problem Difficult inference in irregular statistical models.
method Modified likelihood ratio statistic (split LRT).
result Works for any parametric and some nonparametric models.
Diffusion models can generalize well even with coarse scores, thanks to the manifold hypothesis.
problem Understanding why diffusion models generate novel samples with coarse scores.
method Exploring the manifold hypothesis to explain diffusion model behavior.
result Diffusion models trained with coarse scores can achieve near-parametric rates of generalization, faster than estimating the full data distribution.
Do two data samples come from different distributions? Recent studies of this fundamental problem focused on embedding probability distributions into sufficiently rich characteristic Reproducing Kernel Hilbert Spaces (RKHSs), to compare distributions by the distance between their embeddings. We show that Regularized Ma…
Local regularization fails in transductive learning for some multiclass problems.
problem Whether local regularization can learn all transductive multiclass problems.
method Provided a negative answer by exhibiting a specific multiclass problem.
result Local regularization cannot learn all transductive multiclass problems.
Residual connections significantly boost the performance of deep neural networks. However, there are few theoretical results that address the influence of residuals on the hypothesis complexity and the generalization ability of deep neural networks. This paper studies the influence of residual connections on the hypoth…
This paper characterizes the conditional distribution properties of the finite sample ridge regression estimator and uses that result to evaluate total regression and generalization errors that incorporate the inaccuracies committed at the time of parameter estimation. The paper provides explicit formulas for those err…
This paper analyzes HTL using stability theory for binary classification.
problem Analyzing HTL's theoretical behavior in binary classification tasks.
method Stability analysis of regularized empirical risk minimizers.
result Derives generalization bounds for training error, excess risk, and cross-validation.
Develops a new model for measuring extremal dependence in financial markets.
problem Lack of suitable models for studying extremal dependence in financial markets.
method Constructs regular variation models on and develops a bivariate measure for asymmetry in extremal dependence.
result Rejects the Efficient Tail Hypothesis for China's futures market and identifies profitable investment opportunities.
Paper develops a new generalization bound using PAC-Bayes theory and Gibbs distributions.
problem Limits of traditional generalization bounds due to complexity measures.
method Leverages PAC-Bayes bounds with Gibbs distributions to derive a flexible generalization bound.
result Derives a generalization bound that can adapt to both hypothesis class and task complexity.
We investigate the generalizability of deep learning based on the sensitivity to input perturbation. We hypothesize that the high sensitivity to the perturbation of data degrades the performance on it. To reduce the sensitivity to perturbation, we propose a simple and effective regularization method, referred to as spe…
Improved MMD test for non-Euclidean data with spectral regularization.
problem Inefficient and impractical MMD goodness-of-fit tests for non-Euclidean data.
method Spectral regularization of MMD test, extending results to general cases.
result Minimax optimal test for non-Euclidean data with appropriate regularization.
Regularized OT improves disentangled latent representations in GANs.
problem Disentangled representation learning in GANs.
method Structured regularization of optimal transport for latent space.
result Regularization leads to informative latent dimensions in GANs.
This paper examines the problem of learning with a finite and possibly large set of p base kernels. It presents a theoretical and empirical analysis of an approach addressing this problem based on ensembles of kernel predictors. This includes novel theoretical guarantees based on the Rademacher complexity of the corres…
Regularization is a well recognized powerful strategy to improve the performance of a learning machine and regularization schemes with are central in use. It is known that different leads to different properties of the deduced estimators, say, regularization leads to smooth estimators while…
New learning rates derived for Tikhonov-regularized problems without kernel assumptions.
problem Learning rates for Tikhonov-regularized learning problems.
method Minimax adaptive rates derived using Fourier isocapacitary condition and interpolation theory.
result Derivation of minimax adaptive rates without requiring kernel assumptions.
New framework for robust hypothesis testing using Sinkhorn uncertainty sets.
problem Non-convex robust hypothesis testing problem.
method Exact mixed-integer exponential conic reformulation and convex approximation.
result Satisfactory testing performance and computational efficiency.
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.
A new learning method uses data to learn from large model sets.
problem Learning with large sets of candidate models where uniform convergence is hard.
method Data-dependent learning that incorporates empirical data less reliant on prior assumptions.
result Demonstrates improved generalization in various learning assumptions.
Paper compares optimal denoising methods for generative models, finding different results based on data regularity.
problem Optimizing denoising in score-based generative models for various data types.
method Comparison of full-denoising and half-denoising approaches, analyzing performance in terms of distribution distances.
result Different denoising methods perform better under different data regularity conditions.
Optimal Rates of Sketched-regularized Algorithms for Least-Squares Regression over Hilbert Spacesstat.ML
We investigate regularized algorithms combining with projection for least-squares regression problem over a Hilbert space, covering nonparametric regression over a reproducing kernel Hilbert space. We prove convergence results with respect to variants of norms, under a capacity assumption on the hypothesis space and a …
Proposes a method for inference in high-dimensional classification with non-differentiable surrogate losses.
problem Lack of inference procedures for identifying driving factors in high-dimensional classification with non-differentiable surrogate losses.
method Kernel-smoothed decorrelated score and cross-fitted version for hypothesis tests and interval estimators.
result Valid and superior inference methods for high-dimensional classification with non-differentiable surrogate losses.
Paper investigates hardness of learning neural networks under manifold hypothesis.
problem Hardness of learning neural networks under the manifold hypothesis.
method Extending proofs of hardness in the SQ and cryptographic settings to the geometric setting.
result Learning is hard under input manifolds of bounded curvature but learnable with additional assumptions on manifold volume.
Dropout increases the generalization of neural networks by expanding the weight space.
problem Understanding and improving the generalization of neural networks.
method Introducing weight expansion and showing that dropout leads to it.
result Dropout increases the generalization of neural networks by expanding the weight space.
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…
In this paper, we consider a generic probabilistic discriminative learner from the functional viewpoint and argue that, to make it learn well, it is necessary to constrain its hypothesis space to a set of non-trivial piecewise constant functions. To achieve this goal, we present a scalable unsupervised regularization f…
Proper learning is possible with labeled data, but unlabeled data can improve performance.
problem Problems that can only be learned improperly, like multiclass classification.
method Distributional regularization and worst-case performance evaluation.
result Proper learnability is possible under certain conditions involving unlabeled data.
This work builds the connection between the regularity theory of optimal transportation map, Monge-Ampère equation and GANs, which gives a theoretic understanding of the major drawbacks of GANs: convergence difficulty and mode collapse. According to the regularity theory of Monge-Ampère equation, if the support of the …
Pruning improves model generalization in over-parameterized models, contradicting traditional theories.
problem Pruning's effect on generalization in over-parameterized models.
method Empirical study on standard pruning algorithms and additional regularization effects.
result Pruning leads to better training and regularization, improving generalization.
Unified view of score estimators for flexible densities.
problem Estimating the score from unknown distributions.
method Regularized nonparametric regression framework.
result Unified convergence analysis and new estimators with desirable properties.
We investigate the continuity of expected exponential utility maximization with respect to perturbation of the Sharpe ratio of markets. By focusing only on continuity, we impose weaker regularity conditions than those found in the literature. Specifically, we require, in addition to the -compactness hypothesis of La…
Paper tackles functional linear regression using spectral algorithms with discrete observations.
problem Functional linear regression problem with discretely observed data.
method Combines distributed spectral algorithms with Sobolev kernels for regularization.
result Derives matching upper and lower bounds for convergence in Sobolev norm.
Obtaining deep networks that are robust against adversarial examples and generalize well is an open problem. A recent hypothesis even states that both robust and accurate models are impossible, i.e., adversarial robustness and generalization are conflicting goals. In an effort to clarify the relationship between robust…
In the supervised learning setting termed Multiple-Instance Learning (MIL), the examples are bags of instances, and the bag label is a function of the labels of its instances. Typically, this function is the Boolean OR. The learner observes a sample of bags and the bag labels, but not the instance labels that determine…
New bounds improve generalization in learning scenarios.
problem Limitations of existing information-theoretic bounds in SCO problems.
method Sample-conditioned hypothesis stability and neighboring-hypothesis matrix.
result Sharper generalization guarantees in various learning scenarios.
-regularization has been demonstrated to be an attractive technique in machine learning and statistical modeling. It attempts to improve the generalization (prediction) capability of a machine (model) through appropriately shrinking its coefficients. The shape of a estimator differs in varying choices of the…
The paper proposes a bio-inspired framework for better compression and adversarial robustness in machine learning models.
problem Machine learning models are vulnerable to adversarial examples.
method The paper introduces a bio-inspired classification framework that conditions model inference on label hypothesis and uses an information bottleneck regularizer.
result The framework enables better compression and adversarial robustness without loss of natural accuracy.
Study of regularized least squares in RKKS with indefinite kernels.
problem Asymptotic properties of regularized least squares with indefinite kernels in RKKS.
method Introducing a bounded hyper-sphere constraint, theoretical demonstration of globally optimal solution, modified error decomposition techniques, matrix perturbation theory.
result Derivation of learning rates in RKKS, same as RKHS under certain conditions.
We give a necessary and sufficient geometric structural condition for a stable codimension 1 integral varifold on a smooth Riemannian manifold to correspond to an embedded smooth hypersurface away from a small set of generally unavoidable singularities; when this condition is satisfied, the singular set is empty if the…
This paper proposes a new optimization objective for value-based deep reinforcement learning. We extend conventional Deep Q-Networks (DQNs) by adding a model-learning component yielding a transcoder network. The prediction errors for the model are included in the basic DQN loss as additional regularizers. This augmente…
The goal of regression and classification methods in supervised learning is to minimize the empirical risk, that is, the expectation of some loss function quantifying the prediction error under the empirical distribution. When facing scarce training data, overfitting is typically mitigated by adding regularization term…