We find a convex model for traditional nonlinear regression under L2 loss.
problem Nonlinear regression under L2 loss with non-convex optimization.
method Showed a convex nonlinear regression model for least squares problem.
result Existence of a convex model simplifies training complex systems.
Conventional research attributes the improvements of generalization ability of deep neural networks either to powerful optimizers or the new network design. Different from them, in this paper, we aim to link the generalization ability of a deep network to optimizing a new objective function. To this end, we propose a \…
We consider the problem of learning a forest of nonlinear decision rules with general loss functions. The standard methods employ boosted decision trees such as Adaboost for exponential loss and Friedman's gradient boosting for general loss. In contrast to these traditional boosting algorithms that treat a tree learner…
Extends return extrapolation to nonlinear, asymmetric functions under stochastic volatility.
problem Behavioral anomalies in portfolio choice under stochastic volatility.
method Smooth, nonlinear, asymmetric extrapolation function; CRRA investor; Heston stochastic volatility; Hamilton-Jacobi-Bellman equation; Numerical solutions (finite-difference ADI, deep learning-driven iterative).
result Saturation acts as an endogenous correction mechanism, reducing welfare loss.
Regularizers change the geometric properties of loss functions in neural networks.
problem Understanding how different regularizers affect the geometric properties of loss functions in neural networks.
method Examined several regularizers, including weight decay, to determine if the regularized loss function becomes Morse.
result For certain regularizers, the regularized loss function becomes Morse, indicating a change in geometric properties.
A novel dictionary-based approach for predicting functions.
problem Functional-output regression with non-orthogonal dictionaries.
method Projection learning (PL) with reproducing kernel Hilbert spaces (KPL).
result KPL offers a flexible and computationally efficient solution.
New algorithms achieve decision calibration without sample complexity dependent on feature dimension.
problem Achieving decision calibration for nonlinear loss functions with polynomial sample complexity.
method Developed smooth relaxation of decision calibration, enabling dimension-free algorithms.
result Efficient algorithms post-process predictors to satisfy decision calibration without worsening accuracy.
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…
New algorithms estimate Jacobian matrices for large-scale machine learning.
problem Efficiently computing search directions for large nonlinear least squares.
method Exploit low-rank structure in Hessian to estimate Jacobian matrices.
result Two algorithms perform well compared to state-of-the-art methods.
Leveled Homomorphic Encryption (LHE) offers a potential solution that could allow sectors with sensitive data to utilize the cloud and securely deploy their models for remote inference with Deep Neural Networks (DNN). However, this application faces several obstacles due to the limitations of LHE. One of the main probl…
New deep learning method solves complex BSDEs efficiently.
problem Solving high-dimensional nonlinear BSDEs.
method Reformulate as global optimization, approximate solution with deep neural network, globally minimize quadratic local loss functions.
result Demonstrated effectiveness on various high-dimensional nonlinear BSDEs, including finance applications.
The paper explores how the depth of neural networks affects their ability to represent data accurately.
problem Understanding the implicit bias and rank of neural networks with large depth.
method Analyzing the convergence of representation cost to a notion of rank as network depth increases, and investigating conditions for recovering the true rank of data.
result There is a range of network depths where the true rank of data is recovered, and this affects the topology of class boundaries.
We extend return extrapolation to incorporate asymmetry and saturation, finding that asymmetric nonlinear extrapolation leads to lower welfare loss.
problem Optimal portfolio choice under stochastic volatility
method Smooth, nonlinear extrapolation function with sentiment and variance hedging
result Lower welfare loss with asymmetric nonlinear extrapolation
The past decade has witnessed a successful application of deep learning to solving many challenging problems in machine learning and artificial intelligence. However, the loss functions of deep neural networks (especially nonlinear networks) are still far from being well understood from a theoretical aspect. In this pa…
Spectral deconfounding improves machine learning models by reducing hidden confounding effects.
problem Machine learning models can be misled by hidden confounders, leading to unreliable predictions.
method Develops a nonlinear spectral deconfounding framework for gradient boosting that modifies boosting dynamics to slow down in confounding-aligned directions.
result Spectrally deconfounded boosting improves estimation of the target function under hidden confounding and is more scalable.
We introduce nonlinear higher-order label spreading for semi-supervised learning.
problem Efficient semi-supervised learning on graphs with complex label spreading.
method We add nonlinearity to label spreading through higher-order graph structures, proving convergence and demonstrating efficiency on various datasets.
result Our nonlinear higher-order label spreading algorithm converges to the global solution and performs favorably compared to classical methods.
Gradient descent on ReLU networks with square loss implicitly favors balanced weights.
problem Understanding implicit regularization in nonlinear neural networks with regression losses.
method Analyzing gradient descent dynamics on ReLU networks with square loss.
result It is impossible to characterize the implicit regularization of ReLU networks with square loss by any explicit function of model parameters.
Machine Learning improves macroeconomic forecasting by capturing nonlinearities.
problem Improving macroeconomic forecasting accuracy.
method Study four features (nonlinearities, regularization, cross-validation, loss function) in data-rich and data-poor environments.
result Nonlinearity is the key to improving forecasting accuracy.
This paper tackles efficient optimization for nonlinear embeddings in similarity learning.
problem Learning similarity with nonlinear embeddings is challenging due to the large number of pairs.
method Detailed derivations and efficient optimization methods for nonlinear embeddings are developed.
result Efficient optimization methods for nonlinear embeddings are shown to be highly effective.
Proposes IIB for domain generalization, overcoming failure modes of IRM.
problem Domain generalization with nonlinear classifiers and pseudo-invariant features.
method Invariant Information Bottleneck (IIB) using mutual information and variational formulation.
result Significantly outperforms IRM on synthetic datasets and real-world benchmarks.
Due to the success of deep learning to solving a variety of challenging machine learning tasks, there is a rising interest in understanding loss functions for training neural networks from a theoretical aspect. Particularly, the properties of critical points and the landscape around them are of importance to determine …
Unified framework detects change-points and estimates parameters in nonlinear systems with regime switching.
problem Detecting change-points and estimating parameters in nonlinear dynamical systems with regime transitions.
method Residual-loss anomaly analysis of physics-informed neural networks, two-stage strategy.
result The method outperforms traditional approaches in change-point localization and parameter estimation accuracy.
Custom loss functions improve accuracy of wildfire rate of spread forecasts.
problem Improving accuracy of wildfire rate of spread forecasts.
method Examined custom loss functions in machine learning models of fuel moisture content.
result Custom loss functions improved accuracy of ROS forecasts by a small amount.
ADMM algorithm solves nonlinear matrix decompositions efficiently.
problem Nonlinear matrix decompositions for various applications.
method Alternating Direction Method of Multipliers (ADMM) for nonlinear matrix factorization.
result The method efficiently solves diverse nonlinear matrix decompositions.
New machine learning methods solve complex PDEs with improved accuracy.
problem Solving fully nonlinear PDEs with convex Hamiltonian.
method Rewriting PDE in dual stochastic control form, estimating optimal feedback control with neural network, approximating value function with neural networks.
result Improved estimation of PDE solution and its derivatives, especially the second derivative.
We present a new machine learning approach to estimate personalized treatment effects in the classical potential outcomes framework with binary outcomes. To overcome the problem that both treatment and control outcomes for the same unit are required for supervised learning, we propose surrogate loss functions that inco…
The paper introduces a new method for risk measurement using weak optimal transport.
problem Risk measurement in insurance and financial contexts.
method Convex risk measures with weak optimal transport penalties, explicit representation via nonlinear transform, computational aspects, and approximations using neural networks.
result Explicit representation and computational methods for risk measures.
Noise balance theory explains SGD's behavior in neural networks.
problem Understanding SGD's navigation in neural network loss landscapes.
method Analyzes minibatch noise and loss function symmetries.
result Derives the stationary distribution of SGD for deep networks.
Framework for designing nonlinearities in neural networks with slope constraints.
problem Designing nonlinearities with specific properties for signal processing.
method Variational framework with regularization for slope constraints and optimization of adaptive splines.
result Adaptive nonuniform linear splines achieve global optimum in constrained optimization.
We solve a high-dimensional model where nonlinear autoencoders detect hidden structure missed by PCA.
problem Hidden structure in high-dimensional data not detected by PCA.
method Tractable spiked model with two latent factors, one visible and one uncorrelated.
result Nonlinear autoencoders can extract hidden structure missed by PCA, even if reconstruction loss is higher.
This paper extends performative prediction to nonlinear cases.
problem Performative prediction's effectiveness is limited by linear assumptions in real-world applications.
method Formulated a maximum margin approach loss function and extended it to nonlinear spaces using kernel methods.
result Derived conditions for performative stability in both linear and nonlinear cases.
Proposes a new AFT model for nonlinear survival data.
problem Limited ability of classical AFT models to represent nonlinear relationships and handle complex covariate structures.
method Structured nonparametric extension using Kolmogorov--Arnold representations and unified censoring-adjusted losses.
result Method captures nonlinear effects and recovers linear structure when appropriate.
Graph neural networks improve volatility forecasting by capturing spillover effects.
problem Forecasting multivariate realized volatility with spillover effects.
method Customized graph neural networks incorporating spillover effects from multi-hop neighbors.
result Modeling nonlinear spillover effects enhances forecasting accuracy, especially for short-term horizons.
New method prevents neural network breakdown by combining trimmed loss and variation regularization.
problem Outlier contamination in neural network training.
method Integrates transformed trimmed loss and higher-order variation regularization.
result Ensures robustness to outlier contamination with a high functional breakdown point.
The paper introduces neural INGARCH models for time series of counts.
problem Analyzing time series of counts using traditional INGARCH models.
method Combining artificial neural networks with INGARCH models.
result Neural INGARCH models outperform traditional models in information loss.
We propose a new algorithm for solving parabolic partial differential equations (PDEs) and backward stochastic differential equations (BSDEs) in high dimension, by making an analogy between the BSDE and reinforcement learning with the gradient of the solution playing the role of the policy function, and the loss functi…
Stochastic descent methods (of the gradient and mirror varieties) have become increasingly popular in optimization. In fact, it is now widely recognized that the success of deep learning is not only due to the special deep architecture of the models, but also due to the behavior of the stochastic descent methods used, …
Two models predict net loan losses using Bayesian and frequentist regression.
problem Predicting net loan losses using financial and sociological data.
method Bayesian and frequentist regression analysis.
result Improved understanding of net loan loss relationships.
Many modern learning tasks involve fitting nonlinear models to data which are trained in an overparameterized regime where the parameters of the model exceed the size of the training dataset. Due to this overparameterization, the training loss may have infinitely many global minima and it is critical to understand the …
In deep learning, \textit{depth}, as well as \textit{nonlinearity}, create non-convex loss surfaces. Then, does depth alone create bad local minima? In this paper, we prove that without nonlinearity, depth alone does not create bad local minima, although it induces non-convex loss surface. Using this insight, we greatl…
This paper addresses tracking of a moving target in a multi-agent network. The target follows a linear dynamics corrupted by an adversarial noise, i.e., the noise is not generated from a statistical distribution. The location of the target at each time induces a global time-varying loss function, and the global loss is…
Deep neural networks improve AFT model for non-linear predictors.
problem Nonlinearity in predictors of AFT models.
method Apply DNNs to fit AFT models using Gehan-type loss and sub-sampling.
result DeepR-AFT outperforms parametric and semiparametric models.
Many real-world analytics problems involve two significant challenges: prediction and optimization. Due to the typically complex nature of each challenge, the standard paradigm is predict-then-optimize. By and large, machine learning tools are intended to minimize prediction error and do not account for how the predict…
Characterizes Hessian eigenspectra for realistic nonlinear models.
problem Understanding Hessian eigenspectra in realistic nonlinear models.
method Deterministic equivalent techniques from random matrix theory.
result Hessian can have qualitatively different spectral behaviors.
Reduces function approximation dimensions from high to low with sparse data.
problem Function approximation from sparse data.
method Nonlinear Level Set Learning (NLL) with geometric information.
result Reduces input dimension to theoretical lower bound with minor accuracy loss.
This paper proposes a Lasso-type estimator for a high-dimensional sparse parameter identified by a single index conditional moment restriction (CMR). In addition to this parameter, the moment function can also depend on a nuisance function, such as the propensity score or the conditional choice probability, which we es…
This paper analyzes optimal consumption strategies for loss-averse investors with multiplicative habit formation.
problem Optimal consumption strategies for loss-averse investors with multiplicative habit formation.
method The study uses a concave envelope of the S-shaped utility function and a nonlinear free boundary problem to analyze the HJB equation.
result The paper provides optimal consumption and investment policies in feedback form.
This work introduces a new loss function to improve the efficiency of optimization-based PDE solvers.
problem Optimization-based PDE solvers converge slowly and are inefficient compared to classical iterative solvers.
method Proposes a novel Stabilized Gradient Residual (SGR) loss function to modulate the condition number.
result The SGR loss achieves orders-of-magnitude faster convergence than the MSE loss in both ODIL and PINNs frameworks.