We characterize the asymptotic performance of nonparametric one- and two-sample testing. The exponential decay rate or error exponent of the type-II error probability is used as the asymptotic performance metric, and an optimal test achieves the maximum rate subject to a constant level constraint on the type-I error pr…
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 “optimal test error”
Adversarial training achieves optimal test error for shallow networks.
problem Achieving optimal adversarial test error for general data distributions.
method Applying new Rademacher complexity bounds and properties of optimal adversarial predictors.
result Adversarial training can achieve optimal adversarial test error for general data distributions.
Optimal AFs minimize RFR test error and sensitivity.
problem Finding optimal AFs for RFR to minimize test error and sensitivity.
method Closed-form solution for AFs minimizing test error and sensitivity under different functional parsimony.
result Optimal AFs can be linear, saturated linear, or Hermite polynomial expressions.
Paper shows how gradient concentration helps in learning from inexact data.
problem Learning from inexact and stochastic training data.
method Combines probabilistic gradient concentration with inexact optimization techniques.
result Derives sharp test error guarantees for learning.
TCE measures calibration error with a test-based approach.
problem Measuring calibration error of probabilistic binary classifiers.
method TCE uses a novel loss function based on a statistical test.
result TCE offers clear interpretation, consistent scale, and enhanced visual representation.
This article analyzes the weak error of SGD optimization schemes.
problem Analyzing the error in SGD optimization schemes with respect to a test function.
method Weak error analysis for SGD type optimization schemes.
result The weak error decays at the same speed as in the strong sense.
Bayes-optimal learning of deep random networks with Gaussian weights is studied.
problem Learning a target function corresponding to a deep, extensive-width, non-linear neural network with random Gaussian weights.
method Closed-form expressions for Bayes-optimal test error, ridge regression, kernel and random features regression are computed.
result Optimally regularized ridge regression and kernel regression achieve Bayes-optimal performances, while logistic loss yields a near-optimal test error for classification.
We characterize the asymptotic performance of nonparametric goodness of fit testing. The exponential decay rate of the type-II error probability is used as the asymptotic performance metric, and a test is optimal if it achieves the maximum rate subject to a constant level constraint on the type-I error probability. We …
Study loop corrections in random feature models affecting training and test errors.
problem Analyzing loop corrections in random feature models to understand training and test errors.
method Statistical physics and effective field theory approach to study loop corrections.
result Derived loop corrections to training error, test error, and generalization gap.
Tent adapts models during testing by minimizing entropy of predictions.
problem Adapting models to new data during testing with limited information.
method Test entropy minimization (tent) and online channel-wise affine transformations.
result Reduces generalization error on various datasets and benchmarks.
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.
Robust tests control type I error under data corruption.
problem Effective hypothesis testing under data corruption.
method General permutation tests using kernel MMD and HSIC metrics.
result Robust tests are minimax optimal and outperform private tests.
This work finds a point with small test error in polynomial time for mildly overparameterized neural nets.
problem Achieving small test error in mildly overparameterized neural networks.
method The work shows that the landscape of loss functions with explicit regularization has a property that all local minima and certain stationary points achieve small test error. It also proves the existence of polynomial time algorithms for finding such points in convolutional and fully connected neural nets.
result Polynomial time algorithms exist for finding points with small test error in mildly overparameterized neural nets.
DP-SPRT improves privacy in sequential tests with near-optimal error rates.
problem Privacy constraints in sequential probability ratio tests.
method A wrapper for SPRT that uses a private mechanism to determine when to stop based on predefined intervals.
result DP-SPRT achieves near-optimal error rates and privacy guarantees.
SGD reduces test error by decorrelating updates.
problem Improving generalization error in machine learning models.
method Derive a formula for generalization gap change due to SGD updates, compare to GD, and show decorrelation effect.
result SGD implicitly regularizes generalization error by decorrelating updates.
Bayes-optimal learning of a neural network with quadratic activations is achieved with GAMP-RIE.
problem Learning a neural network with quadratic activations from quadratic samples.
method Combining approximate message passing with rotationally invariant matrix denoising.
result Derives a closed-form expression for Bayes-optimal test error.
Near-optimal tests and confidence sequences for non-parametric data.
problem Flexible statistical inference and decision-making with non-parametric data.
method Classic delayed-start normal-mixture sequential probability ratio tests with asymptotic guarantees.
result Asymptotically optimal type-I error and expected rejection time guarantees.
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.
Memorize to Generalize: on the Necessity of Interpolation in High Dimensional Linear Regressionstat.ML
Optimal machine learning requires interpolating training data in high-dimensional linear regression.
problem Achieving optimal predictive risk in overparameterized linear regression models.
method Analyzing proportional asymptotics of random design and label noise variance.
result Optimal performance in linear regression requires fitting training data to higher accuracy than inherent noise.
We find a deterministic equivalent for random feature regression's test error, independent of feature map dimension.
problem Understanding the generalization performance of random feature ridge regression.
method We derive a deterministic equivalent for the test error of RFRR under a concentration property, showing it can be approximated by a closed-form expression dependent on feature map eigenvalues.
result Our approximation guarantee is non-asymptotic, multiplicative, and independent of the feature map dimension, providing a tight result for the smallest number of features achieving optimal minimax error rate.
Optimizes group testing for COVID-19 to reduce test numbers.
problem Minimizing tests for accurate infection detection.
method Bayesian approach with genetic algorithms and sub-modularity.
result Greedy-adaptive method provides theoretical guarantees.
Paper analyzes holdout cross-validation for large non-Gaussian covariance estimation.
problem Estimating large covariance matrices for non-Gaussian data.
method Use of Weingarten calculus and Ledoit-Péché formula for theoretical error derivation.
result Optimal train-test split ratio is proportional to square root of matrix dimension.
In this paper, we bound the error induced by using a weighted skeletonization of two data sets for computing a two sample test with kernel maximum mean discrepancy. The error is quantified in terms of the speed in which heat diffuses from those points to the rest of the data, as well as how at the weights on the refere…
The paper tackles data misappropriation in LLMs by embedding watermarks and testing for their presence.
problem Detecting data misappropriation in LLMs trained on copyrighted data.
method Embedding watermarks, formulating as hypothesis testing, developing statistical framework, constructing test statistics, determining optimal thresholds, controlling errors, establishing asymptotic optimality.
result The proposed statistical testing framework effectively detects data misappropriation in LLMs.
Equivalent tests for SGD batch size selection found.
problem Finding equivalent tests for adaptive batch size selection in SGD.
method Norm and inner product/orthogonality tests equivalence demonstration.
result Norm and inner product/orthogonality tests are equivalent under specific conditions.
We study the error landscape of deep linear and nonlinear neural networks with the squared error loss. Minimizing the loss of a deep linear neural network is a nonconvex problem, and despite recent progress, our understanding of this loss surface is still incomplete. For deep linear networks, we present necessary and s…
The Perils of Optimizing Learned Reward Functions: Low Training Error Does Not Guarantee Low Regretcs.LG
Learning reward functions can lead to poor policy performance despite low error.
problem Low error in learned reward functions does not guarantee low regret in policy performance.
method Mathematical analysis of reward learning and policy optimization.
result A low expected test error of the reward model guarantees low worst-case regret, but error-regret mismatch can occur with certain data distributions.
New method controls false discoveries in real-time data streams.
problem Online testing of hypotheses with strict error constraints and no future data.
method Structure-adaptive sequential testing (SAST) with alpha-investment algorithm.
result Substantial power gain over existing online testing rules.
Sequential Kernel-based Conditional Independence Testing via Adaptive Betting
problem Testing conditional independence
method Testing-by-betting on an adaptively optimized Kernel Conditional Independence statistic
result Significantly reduces Type I error inflation while preserving high power
GAAVI offers anytime-valid tests for CMF global null and contrasts.
problem Inference on the conditional mean function for high confidence decisions.
method Asymptotic anytime-valid tests for CMF global null and contrasts.
result Achieves asymptotic type-I error guarantees, power one, and optimal sample complexity.
New method improves experimental design under model misspecification.
problem Improving experimental design under time and budget constraints with model misspecification.
method Developed a new acquisition function (R-IDeA) that targets representativeness, informativeness, and de-amplification.
result The new method outperforms methods focusing on representativeness or informativeness alone.
We consider the weak detection problem in a rank-one spiked Wigner data matrix where the signal-to-noise ratio is small so that reliable detection is impossible. We propose a hypothesis test on the presence of the signal by utilizing the linear spectral statistics of the data matrix. The test is data-driven and does no…
A new BO termination criterion for HPO reduces optimization time without sacrificing test performance.
problem Determining an optimal budget for hyperparameter optimization.
method A new termination criterion based on the discrepancy between predictive and computable target performance.
result The proposed termination criterion achieves a better trade-off between test performance and optimization time.
The study sets limits on how robust classifiers can be against adversarial attacks.
problem Understanding the limits of robustness in classification models against adversarial attacks.
method Utilized optimal transport theory to derive variational formulae and explicit lower-bounds on Bayes-optimal error.
result Explicit lower-bounds on the Bayes-optimal error for distance-based attacks, universal in geometry of class-conditional distributions.
Sequential hypothesis testing is a desirable decision making strategy in any time sensitive scenario. Compared with fixed sample-size testing, sequential testing is capable of achieving identical probability of error requirements using less samples in average. For a binary detection problem, it is well known that for k…
In this paper, we consider the problem of learning an unknown graph via queries on groups of nodes, with the result indicating whether or not at least one edge is present among those nodes. While learning arbitrary graphs with nodes and edges is known to be hard in the sense of requiring $Ω( \min\{ k^2 \log n, …
Transforms any test into anytime-valid with sample savings.
problem Sequential data invalidates classical test guarantees.
method Predicts test outcomes to create anytime-valid stopping rules.
result Ensures Type-I error control and near-optimal power.
Minimizes indecisions in selective classification to control misclassification rates.
problem Controlling misclassification rates in high-risk scenarios.
method Using indecisions to control misclassification rates, even below Bayes optimal.
result Control of misclassification rates to any user-specified level, even below Bayes optimal.
Stochastic linear optimization never overfits with quadratically-bounded losses on general datacs.LG
New bounds show linear predictors rarely overfit with certain optimization methods.
problem Bounding test error for linear predictors with stochastic optimization methods.
method Coupling argument for fixed point methods like stochastic and batch mirror descent.
result Locally-adapted rates that depend on predictor properties, not global problem structure.
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.
A new witness two-sample test improves data efficiency and power.
problem Nonparametric two-sample testing.
method Optimizes kernel and defines weights and basis points using training data.
result The new test is consistent, has well-controlled type-I error, and has comparable or higher power.
Paper studies distributed learning with limited communication bits, achieving optimal error exponents.
problem Distributed hypothesis testing with constant communication bits.
method Geometric approach in distribution spaces, encoding empirical distributions to transmission bits.
result Optimal achievable error exponents and coding schemes for various communication constraints.
Improved machine learning models outperform their simpler counterparts by using imperfect labels.
problem Improving model performance using imperfect labels.
method Random feature ridge regression (RFRR) with a deterministic equivalent for excess test error.
result The student model can outperform the teacher model regardless of the teacher's scaling law, achieving the minimax optimal rate.
A permutation-based SW test achieves minimax-optimal power for two-sample testing.
problem Nonparametric two-sample testing using the sliced Wasserstein distance.
method Proposes a permutation-based SW test and analyzes its performance.
result Achieves minimax separation rate over multinomial and bounded-support alternatives.
New tests for binary classification regression functions without distribution assumptions.
problem Testing regression functions in binary classification without distributional assumptions.
method Conditional kernel mean embeddings and resampling-based framework.
result Distribution-free hypothesis tests with exact type I error control.
FLOPART solves peak detection by creating accurate train and test set predictions.
problem Correctly detecting peaks in sequential data.
method Dynamic programming changepoint algorithm with zero train label errors.
result FLOPART provides highly accurate predictions on both train and test sets.
Bottlenecks of binary classification from positive and unlabeled data (PU classification) are the requirements that given unlabeled patterns are drawn from the test marginal distribution, and the penalty of the false positive error is identical to the false negative error. However, such requirements are often not fulfi…
Pareto Testing optimizes model performance under multiple constraints.
problem Optimizing machine learning models with multiple conflicting objectives.
method Two-stage process combining optimization and statistical testing.
result Models can be configured to satisfy multiple statistical guarantees and objectives.