The classical notion of comonotonicity has played a pivotal role when solving diverse problems in economics, finance, and insurance. In various practical problems, however, this notion of extreme positive dependence structure is overly restrictive and sometimes unrealistic. In the present paper, we put forward a notion…
Sparse-penalized deep neural networks improve performance in weakly dependent processes.
problem Nonparametric regression and classification under weak dependence.
method Sparse-penalized deep neural networks with oracle inequalities and convergence rates established.
result The proposed estimators outperform non-penalized ones in simulations.
The paper develops a deep neural network estimator for weakly dependent processes with various loss functions.
problem Learning weakly dependent processes with a broad class of loss functions.
method Sparse-penalized deep neural networks with ψ-weak dependence structure and θ∞-coefficients. result Oracle inequalities for the excess risk of the sparse-penalized deep neural networks estimators.
Deep neural nets learn from weakly dependent processes.
problem Learning from ψ-weakly dependent processes. method Deep neural networks for ψ-weakly dependent processes. result Established consistency of empirical risk minimization algorithm and generalization bound.
Study rough volatility models using path-dependent PDEs and fractional Brownian motions.
problem Modeling and analyzing rough volatility in financial markets.
method Showed conditional expectations are unique classical solutions to path-dependent PDEs derived from functional Itô formula. Leverage these to study weak rates of convergence for discretized stochastic integrals.
result Obtained optimal weak error rates for approximating log-stock prices in rough volatility models.
Paper investigates conditions for independence of weak gradients on metric spaces.
problem Dependence of weak gradients on p in arbitrary metric measure spaces. method Investigates the Bounded Interpolation Property to ensure independence of weak gradients.
result Bounded Interpolation Property guarantees independence of weak gradients.
We present a graphical criterion for reading dependencies from the minimal directed independence map G of a graphoid p when G is a polytree and p satisfies composition and weak transitivity. We prove that the criterion is sound and complete. We argue that assuming composition and weak transitivity is not too restrictiv…
Labeling training data is a key bottleneck in the modern machine learning pipeline. Recent weak supervision approaches combine labels from multiple noisy sources by estimating their accuracies without access to ground truth labels; however, estimating the dependencies among these sources is a critical challenge. We foc…
The paper bounds the excess risk of deep neural networks for weakly dependent processes.
problem Learning with weakly dependent data using deep neural networks.
method Approximation of smooth functions by deep neural networks and a bound on excess risk.
result The excess risk bound for deep learning under weak dependence is close to O(n−1/2) for sufficiently smooth functions. Measuring dependence between two random variables is very important, and critical in many applied areas such as variable selection, brain network analysis. However, we do not know what kind of functional relationship is between two covariates, which requires the dependence measure to be equitable. That is, it gives sim…
Generative models enhance weak supervision for better image classification.
problem Lack of labeled data in supervised learning.
method Fusion of generative adversarial networks and weak supervision.
result Model improves multiclass image classification performance.
Paper analyzes weak-to-strong generalization in CNNs, identifying data-scarce and data-abundant regimes.
problem Weak-to-strong generalization in CNNs trained on weak models.
method Formal analysis of gradient descent dynamics in data-scarce and data-abundant regimes.
result Identifies two regimes and distinct mechanisms of generalization in each.
Study shows financial value of weak information converges in discrete vs continuous markets.
problem Analyzing financial value of weak information in discrete vs continuous markets.
method Defined minimal probability measure and financial value of weak information, then showed convergence.
result Financial value of weak information converges in discrete vs continuous markets.
Weak labels can significantly speed up learning for strong tasks.
problem Learning with limited strong labels.
method Using weak labels to accelerate learning of strong tasks.
result Weak labels can accelerate learning to O(icefrac1n) rate. Study on consistency of ML methods for moving objects in non-stationary environments.
problem Consistency of machine learning methods for moving objects in non-stationary environments.
method Least squares, ridge regression, and ℓs-penalized least squares methods under non-stationary spatial-temporal sampling. result Consistency and asymptotic normality of the estimates under weak conditions.
We investigate the computational aspects of the basket CDS pricing with counterparty risk under a credit contagion model of multinames. This model enables us to capture the systematic volatility increases in the market triggered by a particular bankruptcy. The drawback of this problem is its analytical complication due…
Efficient simulation scheme for rough Heston model reduces computational cost.
problem Accurate and efficient simulation of the rough Heston model for option pricing.
method Weak simulation scheme based on Markovian approximations of the rough Heston process.
result The new scheme exhibits second order weak convergence with linear computational cost.
Self-test loss functions improve data-driven modeling of weak-form operators and gradient flows.
problem Challenges in selecting test functions for data-driven modeling involving weak-form operators and gradient flows.
method Introducing self-test loss functions that depend on unknown parameters and are quadratic.
result Self-test loss functions conserve energy for gradient flows and coincide with log-likelihood ratios for stochastic differential equations.
As machine learning models continue to increase in complexity, collecting large hand-labeled training sets has become one of the biggest roadblocks in practice. Instead, weaker forms of supervision that provide noisier but cheaper labels are often used. However, these weak supervision sources have diverse and unknown a…
This paper proves that one-relator groups have a weak Z-structure.
problem The existence of weak Z-structures for all groups of type F.
method Analyzing the geometric properties of one-relator groups and their boundaries.
result Torsion-free one-relator groups have a weak Z-structure.
We study the time dependent cross correlations of stock returns, i.e. we measure the correlation as the function of the time shift between pairs of stock return time series using tick-by-tick data. We find a weak but significant effect showing that in many cases the maximum correlation is at nonzero time shift indicati…
An algorithm learns from multiple models to match an oracle's risk.
problem Learning from multiple noisy models to estimate a target parameter.
method Elimination rounds algorithm for adaptive learning.
result Risk of weak-oracle learner matches that of an oracle in multiple source case.
New method improves tensor completion for weakly-dependent spatiotemporal data.
problem Improving tensor completion for weakly-dependent data on graphs.
method Introducing L1-norm and Graph Laplacian penalties for low-rank tensor decomposition and completion. result Improved performance in metro passenger flow prediction.
We introduce a new functional measure of tail dependence for weakly dependent (asymptotically independent) random vectors, termed weak tail dependence function. The new measure is defined at the level of copulas and we compute it for several copula families such as the Gaussian copula, copulas of a class of Gaussian mi…
The paper develops a method to model high-dimensional data with many variables and weak signals.
problem Modeling high-dimensional dependent data with many explanatory variables and low signal-to-noise ratio.
method Penalized regression for high-dimensional data, factor modeling of residuals, high-dimensional white noise testing, projected Principal Component Analysis.
result Established asymptotic properties of the proposed method for high-dimensional data.
Active WeaSuL uses active learning to improve weak supervision for better model performance.
problem Limited labelled data in machine learning.
method Combines active learning with weak supervision to improve probabilistic labels.
result Active WeaSuL outperforms weak supervision and active learning with limited labelled data.
The weak variance-alpha-gamma process is a multivariate Lévy process constructed by weakly subordinating Brownian motion, possibly with correlated components with an alpha-gamma subordinator. It generalises the variance-alpha-gamma process of Semeraro constructed by traditional subordination. We compare three calibrati…
In the category of metrics with conical singularities along a smooth divisor with angle in (0,2π), we show that locally defined weak solutions (C1,1−solutions) to the Kähler-Einstein equations actually possess maximum regularity, which means the metrics are actually Hölder continuous in the singular polar coord…
For contact manifolds in dimension three, the notions of weak and strong symplectic fillability and tightness are all known to be inequivalent. We extend these facts to higher dimensions: in particular, we define a natural generalization of weak fillings and prove that it is indeed weaker (at least in dimension five),w…
Study improves cryptocurrency price prediction using unlabeled text data.
problem Predicting cryptocurrency returns from unlabelled text data.
method Introduced weak learning approach to finetune BERT on unlabeled text data.
result Finetuning pretrained NLP models with weak labels enhances forecast accuracy.
End-to-end approach for weak supervision improves downstream model performance.
problem Data-labeling bottleneck in machine learning applications.
method Directly learning the downstream model by maximizing its agreement with probabilistic labels generated from weak supervision sources.
result Improved performance over prior work in terms of downstream model performance and robustness.
Geom-GCN improves graph neural networks by preserving structural information and capturing long-range dependencies.
problem Weaknesses in MPNNs' aggregators: loss of structural information and lack of long-range dependencies.
method Proposes a geometric aggregation scheme with three modules: node embedding, structural neighborhood, and bi-level aggregation.
result Achieved state-of-the-art performance on various graph datasets.
Pairwise "same-cluster" queries are one of the most widely used forms of supervision in semi-supervised clustering. However, it is impractical to ask human oracles to answer every query correctly. In this paper, we study the influence of allowing "not-sure" answers from a weak oracle and propose an effective algorithm …
Unified approach for multicalibration in weakly supervised learning.
problem Existing multicalibration methods require clean input-label pairs, which are unavailable in weakly supervised learning.
method Developed estimators and post-hoc correction methods for multicalibration under weak supervision.
result Unified framework for estimating and correcting multicalibration under weak supervision with finite-sample guarantees.
This short note suggests a heuristic method for detecting the dependence of random time series that can be used in the case when this dependence is relatively weak and such that the traditional methods are not effective. The method requires to compare some special functionals on the sample characteristic functions with…
The paper tackles performative risk optimization under weak convexity assumptions.
problem Optimizing performative risk in a closed-loop prediction system with weak convexity.
method Relaxing convexity assumptions to maintain optimization feasibility.
result Iterative optimization methods remain applicable even with weakened convexity conditions.
Improved multi-class AdaBoost algorithm with stronger weak learnability condition.
problem Multi-class classification problem with at least two labels.
method Recursive ensemble algorithm inspired by SAMME, strengthening weak learnability condition.
result Final hypothesis converges to correct label with probability 1 and generalization error bounds exponentially.
The existence of \emph{weak conical Kähler-Einstein} metrics along smooth hypersurfaces with angle between 0 and 2π is obtained by studying a smooth continuity method and a \emph{local Moser's iteration} technique. In the case of negative and zero Ricci curvature, the C0 estimate is unobstructed; while in the ca…
New algorithms solve weak optimal transport problems for nonlinear costs.
problem Computing weak optimal transport with nonlinear costs.
method Mirror descent algorithms for primal and dual versions of WOT.
result Solutions for WOT and WOTUK compared with classical OT.
We determine an explicit presentation by generators and relations of the cohomology algebra H∗(P2∖C,C) of the complement to an algebraic curve C in the complex projective plane P2, via the study of log-resolution logarithmic forms on P2. As a first consequence, we de…
This paper studies a limit order book (LOB) model, in which the order dynamics depend on both, the current best available prices and the current volume density functions. For the joint dynamics of the best bid price, the best ask price, and the standing volume densities on both sides of the LOB we derive a weak law of …
We consider the task of training classifiers without labels. We propose a weakly supervised method---adversarial label learning---that trains classifiers to perform well against an adversary that chooses labels for training data. The weak supervision constrains what labels the adversary can choose. The method therefore…
New theory for PCA under weak latent factors, improving inference and testing.
problem Statistical inference for PCA with weak latent factors and cross-sectional dependence.
method Comprehensive estimation and inference theory for PCA under nearly minimal factor strength, non-asymptotic.
result Asymptotic normality of PCA-based estimator for N≍T with SNR growth rate. The paper establishes bounds on scalar curvature on asymptotically flat manifolds.
problem Establishing scalar curvature bounds on asymptotically flat manifolds.
method Using Ricci-DeTurck flow and distributional scalar curvature, the paper derives bounds on scalar curvature.
result The scalar curvature lower bound under Ricci-DeTurck flow depends on the scalar curvature lower bound in the β-weak sense and time.
Develops weak PINNs for efficient manifold solutions of hyperbolic equations.
problem Challenges in approximating weak solutions of nonlinear hyperbolic equations on manifolds.
method Introduces a novel weak PINN (wPINN) formulation on manifolds leveraging well-posedness theory.
result Demonstrates efficient approximation of entropy solutions on manifolds with a complexity independent of ambient space dimension.
The study provides statistical theory for WGANs in time series forecasting.
problem Statistical analysis of WGANs for time series forecasting.
method Statistical theory and upper bounds for excess Bayes risk, weak convergence, and confidence intervals.
result Developed confidence intervals for time series forecasting using WGANs.
Extends Itô's formula for path-dependent functions in finance.
problem Modeling and hedging of path-dependent financial options.
method Functional extension of Itô's formula for C^{0,1}-functions of continuous weak Dirichlet processes.
result Validates the hedging or superhedging problems for path-dependent options.
Paper relaxes symmetry conditions for universal feature selection in noisy data.
problem Feature selection in noisy data with weak symmetry.
method Developed a universal feature selection framework using singular value decomposition of canonical dependence matrix.
result Selected features achieve asymptotically optimal error exponents up to a residual term.