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.

168,695 papers · 148 categories

Trend · papers per month

147294440587 · Jun 202019922001200920172026
48 results for smoothed analysis

Smoothness analysis of adversarial training reveals LL_\infty constraints cause more non-smoothness.

problem Non-smoothness of adversarial training loss function.
method Analyzed the smoothness of adversarial training loss function using optimal attacks for model parameters.
result The LL_\infty constraint causes more non-smoothness than L2L_2 constraint.

Smoothed analysis of complexity bounds and condition numbers has been done, so far, on a case by case basis. In this paper we consider a reasonably large class of condition numbers for problems over the complex numbers and we obtain smoothed analysis estimates for elements in this class depending only on geometric inva…

2006-05-24abs ↗pdf ↗

Study on optimal rates for sequential probability assignment using smoothed analysis.

problem Optimal rates for sequential probability assignment under smoothed adversaries.
method General-purpose reduction from minimax rates to transductive learning, development of an efficient algorithm using MLE oracle.
result Optimal (logarithmic) fast rates for parametric and finite VC dimension classes, sublinear regret for general classes.

Regularized MFPCA smooths multivariate functional data for clearer patterns.

problem Challenges in controlling roughness of multivariate functional PCs.
method ReMFPCA incorporates a roughness penalty in a penalized framework to smooth PCs.
result Smoothed multivariate functional PCs reveal clearer patterns.

Smoothed analysis is a powerful paradigm in overcoming worst-case intractability in unsupervised learning and high-dimensional data analysis. While polynomial time smoothed analysis guarantees have been obtained for worst-case intractable problems like tensor decompositions and learning mixtures of Gaussians, such guar…

2018-11-29abs ↗pdf ↗

Quantifies polynomial approximation rates for smooth functions under various distributions.

problem Approximating smooth functions with polynomials under different distributional constraints.
method Develops a quantitative analogue of Carleman's theorem using complex analysis.
result Establishes superexponential rates of approximation for certain function classes over general distributions.

Unified approach to discrete and smooth isoperimetric inequalities of arbitrary order.

problem Finding higher order isoperimetric inequalities for both discrete and smooth curves.
method Unified approach via Fourier analysis of linear operators.
result Unified upper and lower bounds for isoperimetric deficit in smooth curves.

Unified analysis of stochastic gradient methods for convex and smooth optimization.

problem Minimizing composite convex and smooth functions.
method Unified convergence analysis of various stochastic gradient methods.
result Unified convergence rates for a variety of methods including proximal SGD, variance reduced methods, quantization, and coordinate descent.

Proposes a neural network autoencoder for smoothing and representation learning of functional data.

problem Lack of sufficient nonlinear representations in existing methods for functional data analysis.
method Develops a neural network autoencoder architecture to process functional data directly, learning both smoothing and representation.
result Outperforms traditional methods in prediction, classification, and computational efficiency.

The paper improves smoothed analysis for online problems with adaptive adversaries.

problem Online prediction, discrepancy minimization, and online optimization with adaptive adversaries.
method General technique to prove smoothed guarantees against adaptive adversaries, reducing to simpler oblivious adversaries.
result Strong smoothed guarantees for three online problems, matching or improving previous results.

New method for faster convergence in non-convex optimization with unbounded smoothness.

problem Finding first-order stationary points of non-convex functions with unbounded smoothness.
method Developed a stopped analysis technique to prove convergence rates for (L0,L1)(L_0,L_1)-smooth functions.
result Achieved O(polylog(T)T)\mathcal{O}(\frac{\mathrm{poly}\log(T)}{\sqrt{T}}) convergence rates without uniform noise bounds.

Decision tree learning heuristics fail even in smoothed analysis for complex targets.

problem Greedy decision tree learning heuristics fail for complex target functions in the smoothed analysis model.
method Construct counterexamples and analyze the behavior of heuristics in the smoothed setting and agnostic setting.
result Greedy decision tree learning heuristics can build trees of exponential depth before achieving high accuracy for certain complex target functions.

DNAMite creates interpretable, calibrated survival analysis models.

problem Limited interpretability in survival analysis models, especially for healthcare applications.
method Feature discretization and kernel smoothing in embedding module for flexible shape functions.
result DNAMite produces calibrated shape functions interpretable as contributions to cumulative incidence function.

The paper proposes a method to compute higher infinitesimals in numerical and symbolic analysis.

problem Computing higher-order derivatives with higher infinitesimals.
method Automatic differentiation in terms of C-infinity rings and Weil algebras.
result A unifying theoretical framework for multivariate higher-order derivatives.

Regularized variants of Principal Components Analysis, especially Sparse PCA and Functional PCA, are among the most useful tools for the analysis of complex high-dimensional data. Many examples of massive data, have both sparse and functional (smooth) aspects and may benefit from a regularization scheme that can captur…

2013-09-11abs ↗pdf ↗

Time series analysis is used to understand and predict dynamic processes, including evolving demands in business, weather, markets, and biological rhythms. Exponential smoothing is used in all these domains to obtain simple interpretable models of time series and to forecast future values. Despite its popularity, expon…

2017-06-09abs ↗pdf ↗

New framework assesses regularization norms in ill-posed problems, revealing L2 instability and proposing adaptive fractional RKHS solutions.

problem Comparative analysis of regularization norms in ill-posed problems.
method Small noise analysis framework for Tikhonov and RKHS regularizations.
result Optimal convergence rates achieved with adaptive fractional RKHS, but hyper-parameters decay too fast.

The paper analyzes MACD using operator theory.

problem Understanding the mathematical foundation of MACD.
method Developed a functional-analytic framework interpreting MACD as a phase-corrected, smoothed derivative operator.
result MACD is structurally equivalent to a band-pass filter and can be expressed as a finite difference of delayed and doubly averaged signals.

New method generates private synthetic data with optimal utility for smooth queries.

problem Achieving strong utility guarantees for meaningful downstream analysis of sensitive datasets.
method Proposes a polynomial-time algorithm for generating (ε,δ)(\varepsilon,δ)-differentially private synthetic data with minimax optimal error rates for smooth queries.
result Achieves a minimax error rate of Ok,d(nmin{1,kd})O_{k,d}(n^{-\min \{1, \frac{k}{d}\}}) for kk-smooth queries, up to a log(n)\log(n) factor.

FedAc accelerates Federated Averaging for distributed optimization.

problem Efficiently optimizing distributed machine learning models.
method Federated Accelerated Stochastic Gradient Descent (FedAc) using a potential-based perturbed iterate analysis.
result FedAc achieves faster convergence and lower communication costs than previous methods.

Smoothed analysis shows that many classes become learnable from positive-only samples.

problem Learning from positive-only samples is challenging due to negative results in worst-case settings.
method Smoothed analysis of positive-only learning, assuming samples from a reference distribution smooth with respect to the true distribution.
result All VC classes become learnable in the smoothed model with O(VC/ε2)O(VC/ε^2) positive samples for εε classification error.

New findings show learning deeper neural networks is hard even with Gaussian inputs and non-degenerate weights.

problem The computational complexity of learning neural networks, especially deeper ones.
method Smoothed analysis framework and local pseudorandom generators.
result Learning depth-3 ReLU networks under Gaussian input distribution is hard even if weight matrices are non-degenerate.

Robust learning method combines kernel smoothing and robust optimization.

problem Certifying robustness against distribution shifts in machine learning models.
method Adapting integral operator using supremal convolution for robustness, leveraging optimal transport.
result The method provides theoretical guarantees for certified robustness and competitive performance.

Improved regret bounds for structured linear contextual bandits with Gaussian noise.

problem Optimizing bandit learning algorithms for structured contexts with Gaussian perturbations.
method Proposed simple greedy algorithms for structured linear contextual bandits with Gaussian noise.
result Unified regret analysis for structured parameters with geometric quantities as bounds.

Oracle-efficient algorithms for online learning with smoothed and hint-adversaries.

problem Online learning with beyond worst-case adversaries.
method Oracle-efficient algorithms for two settings: smoothed analysis and KK-hint transductive learning.
result Oracle-efficient regret bounds for learning real-valued and binary-valued functions.

Improved analysis and new algorithm for gradient-free optimization of smooth functions.

problem Minimization of highly smooth functions with noisy oracle information.
method Two zero-order projected gradient descent algorithms based on randomization over the 2\ell_2 and 1\ell_1 spheres, with improved analysis and theoretical guarantees.
result Improved convergence rates and theoretical guarantees for various function classes.

New algorithm learns halfspaces over hypercube with random bit flips.

problem Agnostic learning of Boolean halfspaces over discrete domains is computationally hard.
method Smoothed analysis with random bit flips for discrete inputs.
result First efficient algorithm for smoothed agnostic learning of halfspaces over Boolean hypercube.

Theoretical analysis of cross-entropy loss functions and their robustness.

problem Guarantees for using cross-entropy as a surrogate loss function.
method Theoretical analysis of a broad family of loss functions, including cross-entropy.
result First HH-consistency bounds for comp-sum losses and smooth adversarial comp-sum losses.

Unified framework for ensemble transport-based smoothing of non-Gaussian time series.

problem Bayesian time series re-analysis with non-Gaussian distributions.
method Measure transport approach to derive consistent prior-to-posterior transformations.
result General ensemble framework for transport-based smoothing of state-space models.

Estimates time-varying network connections using multi-stage smoothing.

problem Estimating edge probabilities of time-varying networks.
method Multi-stage smoothing: temporal local smoothing followed by node-domain smoothing.
result Captures both smooth temporal evolution and structural patterns in connectivity.

This paper analyzes the convergence of Federated Average under relaxed assumptions.

problem Lack of theoretical analysis for Federated Average under assumptions beyond smoothness.
method Relaxing assumptions of strong smoothness to semi-smoothness and semi-Lipschitz properties, and introducing a bound on the gradient.
result Provides a theoretical convergence study on Federated Learning under new assumptions.