We obtain a tight distribution-specific characterization of the sample complexity of large-margin classification with L2 regularization: We introduce the margin-adapted dimension, which is a simple function of the second order statistics of the data distribution, and show distribution-specific upper and lower bounds on…
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.
168,657 papers · 148 categories
Trend · papers per month
48 results for “margin complexity”
Margin enlargement over training data has been an important strategy since perceptrons in machine learning for the purpose of boosting the robustness of classifiers toward a good generalization ability. Yet Breiman (1999) showed a dilemma that a uniform improvement on margin distribution does NOT necessarily reduces ge…
New margin-based learning guarantees improve generalization bounds.
problem Improving generalization bounds for machine learning models.
method Relative deviation margin bounds using empirical margin loss and Rademacher complexity.
result Distribution-dependent generalization bounds for unbounded loss functions.
New probabilistic complexity measures for linear and kernel methods.
problem Limitations of linear and kernel methods in machine learning.
method Introducing approximate notions of dimensional and margin complexity.
result Approximate complexity measures are both sufficient and necessary for learning.
We obtain a tight distribution-specific characterization of the sample complexity of large-margin classification with L_2 regularization: We introduce the γ-adapted-dimension, which is a simple function of the spectrum of a distribution's covariance matrix, and show distribution-specific upper and lower bounds on the s…
New bound on neural network generalization error using geometric complexity.
problem Understanding the generalization capabilities of deep neural networks.
method Derive a new upper bound on generalization error using margin-normalized geometric complexity.
result Empirical validation of the bound for ResNet-18 on CIFAR-10 and CIFAR-100 datasets.
Efficient algorithms improve learning of large-margin halfspaces.
problem Learning large-margin halfspaces efficiently and reproducibly.
method Design of efficient, dimension-independent, polynomial-time algorithms; SGD-based approach; DP-to-Replicability reduction.
result Improved sample complexity compared to previous algorithms, with optimal sample complexity for one algorithm.
Recent research has used margin theory to analyze the generalization performance for deep neural networks (DNNs). The existed results are almost based on the spectrally-normalized minimum margin. However, optimizing the minimum margin ignores a mass of information about the entire margin distribution, which is crucial …
3MSBM learns smooth trajectories from multiple snapshots.
problem Capturing long-range temporal dependencies in complex systems.
method Lifts dynamics to phase space, generalizes stochastic bridges to multi-marginal conditional problems, learns transport maps preserving intermediate marginals.
result Significantly improves convergence and scalability in capturing complex dynamics.
This paper presents a margin-based multiclass generalization bound for neural networks that scales with their margin-normalized "spectral complexity": their Lipschitz constant, meaning the product of the spectral norms of the weight matrices, times a certain correction factor. This bound is empirically investigated for…
We consider the problem of adaptation to the margin and to complexity in binary classification. We suggest an exponential weighting aggregation scheme. We use this aggregation procedure to construct classifiers which adapt automatically to margin and complexity. Two main examples are worked out in which adaptivity is a…
We introduce a simple framework for designing private boosting algorithms. We give natural conditions under which these algorithms are differentially private, efficient, and noise-tolerant PAC learners. To demonstrate our framework, we use it to construct noise-tolerant and private PAC learners for large-margin halfspa…
We present new differentially private algorithms for learning a large-margin halfspace. In contrast to previous algorithms, which are based on either differentially private simulations of the statistical query model or on private convex optimization, the sample complexity of our algorithms depends only on the margin of…
This work proposes a new method to estimate joint probability from pairwise marginals, reducing sample complexity.
problem Direct nonparametric estimation of high-dimensional joint probability is infeasible due to the curse of dimensionality.
method Developed a coupled nonnegative matrix factorization (CNMF) framework using only pairwise marginals.
result The method provably recovers the joint probability mass function up to bounded error in finite iterations under reasonable conditions.
We derive and analyze a new, efficient, pool-based active learning algorithm for halfspaces, called ALuMA. Most previous algorithms show exponential improvement in the label complexity assuming that the distribution over the instance space is close to uniform. This assumption rarely holds in practical applications. Ins…
Efficiently estimates marginal posteriors for complex simulations.
problem Bayesian inference in high-dimensional, intractable likelihood scenarios.
method Simulates and estimates low-dimensional marginal posteriors, using truncated indicators.
result Simulator efficiency and robustness testing of inference results.
Researchers expand on best subset selection theory, identifying key complexities.
problem Understanding model selection performance in high-dimensional sparse linear regression.
method Analyzing residualized signals, orthogonality, and spurious projections to establish margin conditions.
result Established necessary and sufficient margin conditions for BSS model consistency.
Information-Computation Tradeoffs for Learning Margin Halfspaces with Random Classification Noisecs.LG
Study shows a tradeoff between sample complexity and computational efficiency for learning halfspaces with random noise.
problem PAC learning γ-margin halfspaces with Random Classification Noise.
method Established an information-computation tradeoff and provided a simple efficient algorithm with sample complexity O(1/(γ^2 ε^2)). Also, proved lower bounds for SQ algorithms and low-degree polynomial tests.
result Inherent gap between sample complexity and computational efficiency for learning halfspaces with random noise.
One of the main open problems in the theory of multi-category margin classification is the form of the optimal dependency of a guaranteed risk on the number C of categories, the sample size m and the margin parameter gamma. From a practical point of view, the theoretical analysis of generalization performance contribut…
Proposes a new distance metric for multi-marginal optimal transport.
problem Computational scalability in multi-marginal optimal transport.
method Random one-dimensional projections to construct sliced multi-marginal Wasserstein distance.
result Sliced multi-marginal Wasserstein distance is a metric with dimension-free sample complexity.
On the Insufficiency of the Large Margins Theory in Explaining the Performance of Ensemble Methodsstat.ML
Boosting and other ensemble methods combine a large number of weak classifiers through weighted voting to produce stronger predictive models. To explain the successful performance of boosting algorithms, Schapire et al. (1998) showed that AdaBoost is especially effective at increasing the margins of the training data. …
New method controls error in low-dimensional marginals of spatial models.
problem Inaccurate approximation of low-dimensional marginals in spatial models.
method Stein's method with δ-locality condition for spatial models.
result Uniform error bound for marginals of approximate distributions.
Improved Sample Complexities for Deep Networks and Robust Classification via an All-Layer Margincs.LG
For linear classifiers, the relationship between (normalized) output margin and generalization is captured in a clear and simple bound -- a large output margin implies good generalization. Unfortunately, for deep models, this relationship is less clear: existing analyses of the output margin give complicated bounds whi…
Improves sampling from complex hierarchical models using HMC and automatic marginalization.
problem Sampling from complex hierarchical models is difficult for HMC.
method Proposes automatic marginalization as part of the sampling process using HMC in a graphical model extracted from a PPL.
result Significantly improves sampling from real-world hierarchical models.
This work connects the Hessian to the decision boundary complexity in neural networks.
problem Understanding the decision boundary complexity in high-dimensional input space.
method Characterizing the decision boundary using the Hessian top eigenvectors and analyzing the number of outliers.
result The number of outliers in the Hessian spectrum is proportional to the complexity of the decision boundary.
Frugal Flows learn complex data and infer marginal causal effects.
problem Challenges in estimating marginal causal effects from complex data.
method Frugal Flows use normalizing flows to flexibly learn data and infer causal quantities.
result Frugal Flows can generate synthetic data that closely matches real-world data and exactly parameterize causal quantities.
New algorithm learns halfspaces with near-optimal sample complexity in noisy conditions.
problem Learning margin halfspaces with Massart noise.
method Computational efficient algorithm using online SGD on carefully selected convex losses.
result Sample complexity of , nearly matching lower bound.
We consider a problem of risk estimation for large-margin multi-class classifiers. We propose a novel risk bound for the multi-class classification problem. The bound involves the marginal distribution of the classifier and the Rademacher complexity of the hypothesis class. We prove that our bound is tight in the numbe…
Beyond Black-Box Predictions: Identifying Marginal Feature Effects in Tabular Transformer Networkscs.LG
Proposes a tabular transformer model to maintain feature effect intelligibility.
problem Losing marginal feature effects in deep tabular transformer networks.
method Adapts tabular transformer networks to identify marginal feature effects.
result The model accurately identifies marginal feature effects, matching black-box performance while maintaining intelligibility.
A new approach for instance-optimal learning that bypasses impossibility results.
problem Impossibility of achieving marginal-by-marginal guarantees for all marginals.
method Introduces relatively smart learning, which requires competition only with certifiable semi-supervised guarantees.
result One-Inclusion Graph learner is relatively smart up to squaring the sample complexity.
MSBM extends SB for multi-marginal trajectory inference.
problem Trajectory inference from multiple discrete snapshots.
method Multi-Marginal Schrödinger Bridge Matching (MSBM) using iterative Markovian fitting (IMF).
result MSBM effectively captures complex trajectories and respects intermediate distributions.
With an eye toward understanding complexity control in deep learning, we study how infinitesimal regularization or gradient descent optimization lead to margin maximizing solutions in both homogeneous and non-homogeneous models, extending previous work that focused on infinitesimal regularization only in homogeneous mo…
Develops active learning method for linear optimization with margin-based criterion.
problem Optimizing decisions in linear optimization problems with limited labeled data.
method Smart Predict-then-Optimize (SPO) loss and margin-based active learning algorithm.
result Algorithm achieves significantly fewer labels than naive supervised learning, especially for minimizing SPO loss.
MDMA provides closed-form marginals and conditionals for deep networks.
problem Lack of closed-form marginals and conditionals in deep neural models.
method MDMA architecture combining deep scalar representations and hierarchical tensor decompositions.
result MDMA outperforms state-of-the-art models in tasks requiring marginalization and conditional inference.
Neural models improve GLMMs for complex data.
problem Nonlinear relationships in grouped data.
method Replaced linear function with neural networks.
result Improved performance on synthetic and real-world data.
In this paper, we introduce the notion of a quasi-biharmonic submanifold in a pseudo-Riemannian manifold and classify quasi-biharmonic marginally trapped Lagrangian surfaces in Lorentzian complex space forms.
Gradient descent finds halfspaces with low error for agnostic learning.
problem Agnostic learning of linear halfspaces with convex surrogates.
method Gradient descent on convex surrogates for zero-one loss.
result Gradient descent finds halfspaces with error in poly time and sample complexity.
Combines MCTM and NF for flexible multivariate density regression with interpretable marginals.
problem Difficult interpretation of flexible NF models and limitations of MCTM in flexibility.
method Hybrid approach combining MCTM for interpretable marginals and NF for complex joint distributions.
result Demonstrates versatility and improved performance compared to MCTM and other NF models.
The paper improves robust optimization by introducing margin theory.
problem Improving the reliability of solutions in high-dimensional robust optimization.
method Introducing margin theory to improve sample complexity and reliability of solutions.
result The sample complexity of a class of random programs does not depend on the number of variables.
A classical condition for fast learning rates is the margin condition, first introduced by Mammen and Tsybakov. We tackle in this paper the problem of adaptivity to this condition in the context of model selection, in a general learning framework. Actually, we consider a weaker version of this condition that allows one…
Bayesian approach learns invariances from data alone, but last layer approximation is not always sufficient.
problem Learning invariances in neural networks using only training data.
method Bayesian marginal likelihood for last layer, custom optimisation routine, new lower bound.
result Partial success on standard benchmarks and medical imaging dataset, failure on CIFAR10.
New framework for optimal transport with jumps over intermediate spaces.
problem Optimal transport with mass jumps over intermediate spaces.
method Hierarchical Jump multi-marginal transport (HJMOT) on Polish spaces.
result Existence and uniqueness of Monge solutions under sequential differentiability and twist condition.
Gradient descent and SGD achieve low test error in specific network weight regimes.
problem Optimizing two-layer ReLU networks with standard initialization.
method Gradient flow and stochastic gradient descent, analyzing margins and weight norms.
result Gradient descent and SGD can achieve globally maximal margins under certain constraints.
Improved exploration in RL with latent state marginalization.
problem Complexity of deep probabilistic models limits their practical use in reinforcement learning.
method Adopting latent variable policies within the MaxEnt framework, with low-cost marginalization of latent states.
result Effective marginalization leads to better exploration and more robust training.
Recurring international financial crises have adverse socioeconomic effects and demand novel regulatory instruments or strategies for risk management and market stabilization. However, the complex web of market interactions often impedes rational decisions that would absolutely minimize the risk. Here we show that, for…
We give polynomial-time algorithms for the exact computation of lowest-energy (ground) states, worst margin violators, log partition functions, and marginal edge probabilities in certain binary undirected graphical models. Our approach provides an interesting alternative to the well-known graph cut paradigm in that it …
Deep neural network (DNN) regression models are widely used in applications requiring state-of-the-art predictive accuracy. However, until recently there has been little work on accurate uncertainty quantification for predictions from such models. We add to this literature by outlining an approach to constructing predi…
Maximum entropy distributions with discrete support in dimensions arise in machine learning, statistics, information theory, and theoretical computer science. While structural and computational properties of max-entropy distributions have been extensively studied, basic questions such as: Do max-entropy distributio…