The landscape of empirical risk has been widely studied in a series of machine learning problems, including low-rank matrix factorization, matrix sensing, matrix completion, and phase retrieval. In this work, we focus on the situation where the corresponding population risk is a degenerate non-convex loss function, nam…
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
48 results for “population-risk”
Develops local population-risk certificates for model updates
problem Model updates in machine learning
method Certify population-risk increments around a model
result Certified upper endpoint yields a risk-controlled update rule
We show that model compression can improve the population risk of a pre-trained model, by studying the tradeoff between the decrease in the generalization error and the increase in the empirical risk with model compression. We first prove that model compression reduces an information-theoretic bound on the generalizati…
New bounds for KANs trained with DP-SGD, addressing correlated noise.
problem Risk bounds for Kolmogorov-Arnold Networks trained by DP-SGD with correlated noise.
method Established new optimization and population risk analysis for KANs trained with DP-SGD, addressing correlated noise.
result First optimization and population risk analysis of correlated-noise mechanisms for DP training in non-convex settings, including neural networks.
The curse of dimensionality affects neural network optimization, especially with smooth functions.
problem The curse of dimensionality in neural network optimization.
method Examined through the evolution of the parameter distribution under 2-Wasserstein gradient flow.
result The curse of dimensionality persists in neural network optimization, even with smooth functions.
The paper analyzes the maximum margin algorithm's performance on noisy data.
problem Analyzing the performance of maximum margin algorithm on noisy data.
method Finite-sample analysis of maximum margin algorithm applied to noisy data.
result The maximum margin algorithm can achieve nearly optimal population risk with sufficient over-parameterization.
Develops certificates for local population-risk increments using cross-fitted ridge calibration.
problem Certifying local population-risk increments in statistical models.
method Cross-fitted ridge calibration for linear feature classes, separating Taylor fluctuations and remainders.
result Certifies measurable updates from the same sample with penalties dependent on empirical geometry.
Paper improves privacy-preserving optimization rates for convex functions.
problem Differentially private stochastic convex optimization.
method Algorithmic improvements for convex and strongly convex functions under TNC and non-negative loss.
result Excess population risk bounds for DP-SCO are faster than previous results.
Gradient descent learns a single neuron without knowing the relationship between inputs and labels.
problem Learning a single neuron without knowing the relationship between inputs and labels.
method Using gradient descent to minimize empirical risk over i.i.d. samples, with a nonconvex and nonsmooth optimization problem.
result Gradient descent achieves near-optimal population risk in polynomial time and sample complexity.
Population risk is always of primary interest in machine learning; however, learning algorithms only have access to the empirical risk. Even for applications with nonconvex nonsmooth losses (such as modern deep networks), the population risk is generally significantly more well-behaved from an optimization point of vie…
New algorithms for differentially private optimization in convex and non-convex settings with near-optimal rates.
problem Differentially private optimization in convex and non-convex settings.
method Developed algorithms for convex and non-convex settings with near-optimal excess population risk.
result Achieved near-optimal rates in near-linear time for convex settings and nearly dimension independent rates for non-convex settings.
We study the Stochastic Gradient Langevin Dynamics (SGLD) algorithm for non-convex optimization. The algorithm performs stochastic gradient descent, where in each step it injects appropriately scaled Gaussian noise to the update. We analyze the algorithm's hitting time to an arbitrary subset of the parameter space. Two…
New estimates for the population risk are established for two-layer neural networks. These estimates are nearly optimal in the sense that the error rates scale in the same way as the Monte Carlo error rates. They are equally effective in the over-parametrized regime when the network size is much larger than the size of…
In stochastic optimization, the population risk is generally approximated by the empirical risk. However, in the large-scale setting, minimization of the empirical risk may be computationally restrictive. In this paper, we design an efficient algorithm to approximate the population risk minimizer in generalized linear …
Can Shallow Neural Networks Beat the Curse of Dimensionality? A mean field training perspectivecs.LG
Gradient descent struggles with high-dimensional data fitting.
problem Gradient descent struggles with high-dimensional data fitting.
method Gradient descent training of a two-layer neural network on empirical or population risk.
result Gradient descent training may not decrease population risk faster than under mean field scaling.
Novel graph theory for neural networks improves understanding of their structure and performance.
problem Understanding the structural benefits and generalization power of neural networks.
method Developed a novel graph theoretical formulation and extended error analysis for neural networks.
result Similar a priori estimates can be obtained for neural networks under certain conditions, independent of input dimension.
This paper studies the landscape of empirical risk of deep neural networks by theoretically analyzing its convergence behavior to the population risk as well as its stationary points and properties. For an -layer linear neural network, we prove its empirical risk uniformly converges to its population risk at the rat…
This work aims to provide understandings on the remarkable success of deep convolutional neural networks (CNNs) by theoretically analyzing their generalization performance and establishing optimization guarantees for gradient descent based training algorithms. Specifically, for a CNN model consisting of convolution…
The paper addresses differentially private learning for neural networks, focusing on risk bounds and algorithm feasibility.
problem Achieving differentially private learning for neural networks with theoretical guarantees.
method Developed algorithms and theoretical analysis for differentially private stochastic optimization of neural networks.
result Established theoretical bounds for excess population risk in differentially private learning of neural networks.
Paper addresses DP-SCO on heavy-tailed data, providing methods and results.
problem Designing DP algorithms for SCO on heavy-tailed data.
method Sample-and-aggregate framework, gradient smoothing and trimming.
result Achieved DP guarantees for various loss functions with different excess population risks.
Optimal a priori estimates are derived for the population risk, also known as the generalization error, of a regularized residual network model. An important part of the regularized model is the usage of a new path norm, called the weighted path norm, as the regularization term. The weighted path norm treats the skip c…
This work compares regularization and constrained inference for label constraints in machine learning.
problem Improving model performance with label constraints in machine learning.
method Comparison of regularization and constrained inference strategies.
result Constrained inference reduces population risk by correcting model violations, while regularization narrows the generalization gap but introduces bias.
Gradient descent methods for deep ReLU networks achieve optimal generalization rates.
problem Generalization of gradient descent methods for deep neural networks
method Establishing minimax-optimal rates for GD and SGD with deep ReLU networks
result Gradient descent methods for deep ReLU networks achieve optimal generalization rates
New algorithm finds approximate stationary points faster under differential privacy constraints.
problem Finding approximate stationary points of smooth and Lipschitz functions under differential privacy constraints.
method Developed an efficient algorithm that improves convergence rates to stationary points.
result Achieved faster rates of convergence to stationary points in both finite-sum and stochastic settings.
The classical asymptotic theory for parametric -estimators guarantees that, in the limit of infinite sample size, the excess risk has a chi-square type distribution, even in the misspecified case. We demonstrate how self-concordance of the loss allows to characterize the critical sample size sufficient to guarantee …
This work establishes uniform convergence of subdifferentials in stochastic optimization.
problem Understanding how empirical stationary points approximate population ones in nonsmooth, nonconvex stochastic optimization.
method Reduction principle for weakly convex stochastic objectives, focusing on subgradient convergence.
result Sharp uniform convergence rates for subdifferential mappings in stochastic convex-composite optimization.
Paper revisits DP-SCO in Euclidean and spaces, focusing on constrained and bounded sets.
problem Differentially private stochastic convex optimization in constrained and bounded sets in Euclidean and spaces.
method Proposes methods achieving excess population risks dependent on Gaussian width of the constraint set, and novel algorithms for unconstrained and heavy-tailed data.
result Theoretical results for DP-SCO in spaces, including optimal bounds for strongly convex functions.
We provide non-asymptotic excess risk guarantees for statistical learning in a setting where the population risk with respect to which we evaluate the target parameter depends on an unknown nuisance parameter that must be estimated from data. We analyze a two-stage sample splitting meta-algorithm that takes as input ar…
Stacked regressions improve predictive accuracy by combining estimators.
problem Improve predictive accuracy in regression models.
method Analogous to least-squares, learn combination weights by minimizing regularized empirical risk with nonnegativity constraint.
result The stacked estimator has strictly smaller population risk than the best single estimator, especially when signal-to-noise ratio is small.
Stochastic Gradient Descent underperforms on some problems, contrary to expectations.
problem Understanding the generalization performance of SGD on specific problem instances.
method Analysis of stochastic convex optimization framework, proving empirical and generalization gaps for SGD.
result SGD exhibits both empirical risk and generalization gap of on some problem instances, contradicting its conventional understanding.
New stability analysis improves generalization of multipass SGD.
problem Improper preconditioning affects generalization in multipass SGD.
method Developed on-average stability analysis for multipass SGD.
result Proper preconditioning yields optimal effective dimension dependence.
Improved algorithm finds second-order stationary points in non-convex optimization.
problem Minimizing non-convex objectives while preserving training data privacy.
method SpiderBoost framework with two gradient oracles: precise and less precise.
result Improved rates for finding second-order stationary points.
EP-learning framework improves causal contrast estimation efficiency.
problem Estimating heterogeneous causal contrasts efficiently and stably.
method EP-learning framework combining T-learning and DR-learning.
result EP-learners are oracle-efficient and outperform competitors.
Improved analysis for extreme multi-class CRL with better sample complexity.
problem Theoretical sample complexity of CRL in extreme multi-class settings is poorly understood.
method Improved U-Statistics estimator to capture class concentration, proving sample complexity.
result Sample complexity is for extreme multi-class learning, independent of class distribution.
Beyond Consistency: Inference for the Relative risk functional in Deep Nonparametric Cox Modelsstat.ML
Develops asymptotic theory for deep Cox models to enable valid inference.
problem Theoretical gaps in deep neural network estimators for Cox models.
method Asymptotic distribution theory linking in-sample optimization error to population risk.
result Pointwise and multivariate asymptotic normality for subsampled ensemble estimators.
The paper tackles machine unlearning by designing efficient algorithms for adaptive query classes.
problem Designing efficient unlearning algorithms for machine learning models.
method Formalizes the problem and gives efficient unlearning algorithms for linear and prefix-sum query classes.
result Improved guarantees for stochastic convex optimization with reduced unlearning query complexity.
Improved privacy bounds for learning linear predictors with convex losses.
problem Differentially private learning of linear predictors with convex losses.
method Developed private model selection approach to achieve optimal rates.
result Improved upper and lower bounds for excess population risk.
Most high-dimensional estimation and prediction methods propose to minimize a cost function (empirical risk) that is written as a sum of losses associated to each data point. In this paper we focus on the case of non-convex losses, which is practically important but still poorly understood. Classical empirical process …
Study shows benefits of transfer learning with neural networks.
problem Understanding generalization errors in transfer learning.
method Mean-field analysis applied to -ERM and fine-tuning.
result Established conditions for generalization error and convergence rates.
Lessons from Generalization Error Analysis of Federated Learning: You May Communicate Less Often!stat.ML
Study shows more frequent communication in FL reduces model's generalization power.
problem Understanding how often clients should communicate with a server in federated learning.
method PAC-Bayes and rate-distortion theoretic bounds on generalization error.
result More frequent communication with the server decreases model's generalization power.
New algorithms help machines forget old data efficiently.
problem Machine learning models can retain old data, hindering new learning.
method Developed TV-stable algorithms based on noisy SGD for convex and non-convex functions.
result Achieved efficient unlearning with upper and lower bounds on risk.
aLTT selects hyperparameters efficiently with statistical guarantees.
problem Statistical validity and efficiency in hyperparameter selection.
method Sequential data-dependent multiple hypothesis testing with early termination.
result Reduces testing rounds while maintaining statistical validity.
Learning with Locally Private Examples by Inverse Weierstrass Private Stochastic Gradient Descentcs.LG
New algorithm corrects bias in LDP-released data for better analysis.
problem Bias in data released under Local Differential Privacy (LDP).
method Inverse Weierstrass Private Stochastic Gradient Descent (IWP-SGD).
result Converges to true population risk minimizer at rate.
Stochastic Gradient Langevin Dynamics (SGLD) is a popular variant of Stochastic Gradient Descent, where properly scaled isotropic Gaussian noise is added to an unbiased estimate of the gradient at each iteration. This modest change allows SGLD to escape local minima and suffices to guarantee asymptotic convergence to g…
Concentration and excess risk bounds for imbalanced classification with synthetic oversamplingstat.ML
The paper analyzes SMOTE for imbalanced classification, providing theoretical bounds and guidelines.
problem The challenge of imbalanced classification problems, especially with minority classes.
method Theoretical analysis of SMOTE and related oversampling techniques for minority classes.
result Derives concentration and excess risk bounds for SMOTE and kernel-based classifiers.
Near-optimal private tests for simple and MLR hypotheses developed under Gaussian differential privacy.
problem Developing private tests for simple and MLR hypotheses under Gaussian differential privacy.
method A private mean estimator with data-driven clamping bounds, constructing private test statistics.
result Private tests achieve the same asymptotic relative efficiency as non-private most powerful tests.
Early stopping improves neural networks' performance on binary classification tasks.
problem Improving shallow ReLU networks' performance on binary classification tasks.
method Gradient descent with early stopping on binary classification data.
result Gradient descent with early stopping achieves population risk arbitrarily close to optimal.
Study optimizes linear regression analysis for high-dimensional settings.
problem Understanding high-dimensional linear regression with interpolation and regularization.
method Localized uniform convergence analysis of optimistic rates for linear regression.
result Recover guarantees for ridge and LASSO regression under random designs.