New approach to convex hulls for low-rank problems.
problem Characterizing convex hulls for low-rank sets.
method Matrix perspective function and orthogonal projection matrices.
result Strong relaxations for various low-rank problems.
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 “functional perspective”
We propose a new perspective on representation learning in reinforcement learning based on geometric properties of the space of value functions. We leverage this perspective to provide formal evidence regarding the usefulness of value functions as auxiliary tasks. Our formulation considers adapting the representation t…
Examines challenges and proposes new approaches in machine learning theory.
problem Challenges in machine learning as a function approximation and optimization.
method Mathematical analysis of gradient descent, fixed network limitations, and RNNs.
result New insights and mathematical approaches to improve machine learning.
Geometric approach improves functional outlier detection.
problem Detecting outliers in functional data sets.
method Developed a geometric perspective on functional manifold for outlier detection.
result Improved understanding and differentiation of outliers.
The paper tackles noisy functional data by exploring a multivariate perspective.
problem Noisy functional data measured on discrete points.
method Factor model and principal components analysis.
result The latent signal can be accurately estimated using multivariate methods.
Paper develops compact formulations for optimization problems with rank-one convex functions and indicator variables.
problem Optimization problems involving rank-one convex functions with support constraints.
method Perspective reformulation techniques to exploit conic structure and establish convex hull results.
result Systematic perspective formulations for convex hull descriptions of sets with nonlinear separable or non-separable objective functions and combinatorial constraints.
This paper develops a pricing model for data assets from the buyer's perspective.
problem Insufficient research on pricing data assets from the buyer's perspective.
method Develops a pricing model based on the informational value of data assets from the buyer's perspective, using an implicit function derived from value functions in investment-consumption problems under ambiguity markets.
result Derives general expressions and explicit pricing formulas for data assets under various conditions.
Machine learning models predict which ideas will be innovated based on subjective perspectives.
problem Predicting high-impact innovation based on subjective perspectives and interpersonal innovation opportunities.
method Quantifying subjective perspectives and their interaction based on innovator positions within a geometric space of concepts.
result Subjective perspectives predict which ideas individuals and groups will creatively attend to and successfully combine in the future.
Unified perspective on Hopfield networks with attention module.
problem Understanding and optimizing Hopfield networks with attention mechanisms.
method Study of BM counterparts of modern Hopfield networks and their salient properties.
result Introduction of AttnBM with tractable likelihood and gradient.
Review of Gerber-Shiu function for practical actuarial science.
problem Difficulty in numerical approximation and statistical inference of Gerber-Shiu function.
method Comprehensive review of formulations, surplus processes, numerical methods, and statistical inference.
result Enhanced understanding and practical guide for Gerber-Shiu function.
Develops a new theory of loss functions for statistical machine learning.
problem Evaluation of solutions in binary and multiclass classification problems.
method Defines loss functions as subgradients of support functions of convex sets, enabling a calculus of losses.
result Provides a novel perspective on losses and develops a calculus that interpolates between different losses.
New approach to certifiably robust neural networks using Boolean function perspective.
problem Lack of principled understanding and certified robustness for perturbations.
method New perspective on Boolean functions, deriving impossibility results, and developing a unified Lipschitz network.
result Unified Lipschitz network that bypasses expressive power limitations and achieves better certified robustness.
Kernel methods are among the most popular techniques in machine learning. From a frequentist/discriminative perspective they play a central role in regularization theory as they provide a natural choice for the hypotheses space and the regularization functional through the notion of reproducing kernel Hilbert spaces. F…
This paper studies continuum-armed bandits under Besov smoothness conditions and derives minimax rates.
problem Optimizing an unknown function with limited evaluations.
method Studies continuum-armed bandits under Besov smoothness conditions and derives minimax rates.
result Minimax rates over Besov spaces are identical to those over the smallest Hölder space into which Besov spaces embed.
In this paper we construct the quantum group, at roots of unity, of abelian Chern-Simons theory. We then use it to model classical theta functions and the actions of the Heisenberg and modular groups on them.
We take a Hamiltonian-based perspective to generalize Nesterov's accelerated gradient descent and Polyak's heavy ball method to a broad class of momentum methods in the setting of (possibly) constrained minimization in Euclidean and non-Euclidean normed vector spaces. Our perspective leads to a generic and unifying non…
We consider the problem of minimizing a sum of clipped convex functions; applications include clipped empirical risk minimization and clipped control. While the problem of minimizing the sum of clipped convex functions is NP-hard, we present some heuristics for approximately solving instances of these problems. These h…
Synthesizes computational approaches to understand neural timescales.
problem Varying definitions and measurements of neural timescales across studies.
method Reviews data analysis methods, biophysical models, and machine learning models.
result Complements experimental studies with a holistic view of neural timescales.
New definition of stable -th capillary hypersurfaces proposed.
problem Stability of capillary hypersurfaces in different geometries.
method Defining stable -th capillary hypersurfaces as smooth local minimizers of a new energy functional under volume-preserving and contact angle-preserving variations.
result Generalization of stability results to -th capillary hypersurfaces.
This paper presents a basic property of region dividing of ReLU (rectified linear unit) deep learning when new layers are successively added, by which two new perspectives of interpreting deep learning are given. The first is related to decision trees and forests; we construct a deep learning structure equivalent to a …
New method encodes function preferences into neural nets for better generalization.
problem Challenges in encoding explicit function preferences in neural network training.
method Function-space empirical Bayes (FSEB) regularization.
result FSEB leads to near-perfect semantic shift detection and improved generalization.
The thesis presents a new perspective on high-dimensional optimization.
problem The failure point of classical optimization methods in high dimensions.
method A distributional view of optimization, focusing on random objective functions and Bayesian Optimization.
result The distributional view explains predictable progress in high-dimensional optimization and provides insights into optimal step size control.
In this article we raise some new questions about positive definite functions on free groups, and explain how these are related to more well-known questions. The article is intended as a survey of known results that also offers some new perspectives and interesting observations; therefore the style is expository.
Generative adversarial networks (GANs) are successful deep generative models. GANs are based on a two-player minimax game. However, the objective function derived in the original motivation is changed to obtain stronger gradients when learning the generator. We propose a novel algorithm that repeats the density ratio e…
New framework improves adversarial robustness certification for various perturbations.
problem Certifying robustness against adversarial attacks in deep learning models.
method Unified functional optimization approach with non-Gaussian smoothing noise for multiple types of attacks.
result Achieves better certification results and identifies key trade-offs between accuracy and robustness.
Paper connects AJ conjecture and colored Jones polynomial potential function.
problem Relationship between -polynomial and colored Jones polynomial.
method Connects AJ conjecture and colored Jones polynomial potential function.
result Establishes connection between -polynomial and colored Jones polynomial potential function.
Residual Networks (ResNets) have become state-of-the-art models in deep learning and several theoretical studies have been devoted to understanding why ResNet works so well. One attractive viewpoint on ResNet is that it is optimizing the risk in a functional space by combining an ensemble of effective features. In this…
This paper explains why ResNets generalize better than FFNets using neural tangent kernels.
problem Understanding why deep ResNets generalize better than deep FFNets.
method Using neural tangent kernels to compare the learnability of functions induced by the kernels of ResNets and FFNets.
result The kernel of ResNets does not exhibit degeneracy as depth increases, unlike FFNets.
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.
Bayesian deep learning improves neural network accuracy and generalization.
problem Improving accuracy and calibration of deep neural networks.
method Bayesian marginalization and deep ensembles to approximate marginalization, and tempering for calibrating predictive distributions.
result Bayesian approaches improve deep neural networks' accuracy and generalization.
The paper proposes a decoupled approach to efficiently estimate CoVaR, a measure of systemic financial risk.
problem Estimating CoVaR, a measure of systemic financial risk, is challenging due to zero-probability events and portfolio repricing.
method The paper introduces a decoupled approach using smoothing techniques and a functional perspective to model CoVaR.
result The decoupled estimator achieves a rate of convergence of approximately .
Accelerated gradient methods play a central role in optimization, achieving optimal rates in many settings. While many generalizations and extensions of Nesterov's original acceleration method have been proposed, it is not yet clear what is the natural scope of the acceleration concept. In this paper, we study accelera…
New perspective on federated learning as posterior inference, improving optimization.
problem Optimizing global models in distributed learning settings.
method Formulated as posterior inference problem, using MCMC for approximate inference and federated averaging for refinement.
result Federated posterior averaging (FedPA) outperforms existing methods on benchmarks.
Regularization vs. Relaxation: A conic optimization perspective of statistical variable selectioncs.LG
Variable selection is a fundamental task in statistical data analysis. Sparsity-inducing regularization methods are a popular class of methods that simultaneously perform variable selection and model estimation. The central problem is a quadratic optimization problem with an l0-norm penalty. Exactly enforcing the l0-no…
Paper proposes bypassing implicit assumption in GM-based AD methods.
problem Lack of anomalous data and implicit assumption in GM-based AD methods.
method Integrating Discriminative idea to GMM for AD tasks (DiGMM).
result Establishes a connection between generative and discriminative models for AD.
Potential functions can be used as generating potentials of relevant geometric structures for a Riemannian manifold such as the Riemannian metric and affine connections. We study wether this procedure can also be applied to tensors of rank four and find a negative answer. We study this from the perspective of solving t…
Bregman perspective on CART provides a unified framework for impurity measures.
problem Unifying impurity measures in CART
method Bregman divergence approach
result Unified framework for impurity measures
The paper provides bounds for regression schemes using nonstationary training samples.
problem Developing confidence intervals for nonparametric regression with nonstationary data.
method The approach involves Rademacher and Vapnik-Chervonenkis theories to analyze the cost and optimality of regression schemes.
result The paper establishes nonasymptotic bounds for regression schemes and optimality in -distance.
Machine learning techniques are being increasingly used as flexible non-linear fitting and prediction tools in the physical sciences. Fitting functions that exhibit multiple solutions as local minima can be analysed in terms of the corresponding machine learning landscape. Methods to explore and visualise molecular pot…
Gaussian processes help in modeling complex, nonlinear relationships in signal processing.
problem Modeling complex, nonlinear relationships in signal processing.
method Sequential inference for Gaussian processes.
result Gaussian processes enable efficient and accurate modeling of complex relationships.
Datasets with significant proportions of noisy (incorrect) class labels present challenges for training accurate Deep Neural Networks (DNNs). We propose a new perspective for understanding DNN generalization for such datasets, by investigating the dimensionality of the deep representation subspace of training samples. …
Unified approach for quantum and classical learning from evaluation oracles.
problem Learning from evaluation oracles in quantum and classical settings.
method Inspired by Kearns' SQ and Valiant's weak evaluation oracle, a unified framework is established.
result Characterizes query complexity for learning linear function classes and extends learnability results for quantum circuits.
In this paper, we investigate the attractive properties of the proximal gradient algorithm with inertia. Notably, we show that using alternated inertia yields monotonically decreasing functional values, which contrasts with usual accelerated proximal gradient methods. We also provide convergence rates for the algorithm…
Although operator-valued kernels have recently received increasing interest in various machine learning and functional data analysis problems such as multi-task learning or functional regression, little attention has been paid to the understanding of their associated feature spaces. In this paper, we explore the potent…
New differential geometry perspective on orthogonal RNNs.
problem Mitigating exploding and vanishing gradients in RNNs.
method Using tools from differential geometry, parameterizing vector fields via directional derivatives of scalar functions.
result Our approach achieves comparable or better results on benchmark tasks.
Unified theory of deep neural networks with diverse activations.
problem Understanding the relationship between depth and complexity in deep neural networks.
method Developed a unified function space theory for deep networks with various activations.
result Unified theory provides meaningful complexity for deep networks with diverse activations.
Deep learning networks are approximated using dynamical systems theory.
problem Understanding the approximation capabilities of deep learning networks.
method Modeling deep residual networks as continuous-time dynamical systems and using approximation theories in .
result Established general sufficient conditions for universal approximation of deep residual networks.
We establish geometric and topological properties of the space of value functions in finite state-action Markov decision processes. Our main contribution is the characterization of the nature of its shape: a general polytope (Aigner et al., 2010). To demonstrate this result, we exhibit several properties of the structu…