Consistent estimation of constrained autoregressive processes.
problem Estimating autoregressive processes with coefficients constrained to an ellipsoid.
method Use of constrained and penalized estimators under different norms.
result Provide consistency results for estimation of constrained autoregressive processes.
We study a constrained optimal control problem with possibly degenerate coefficients arising in models of optimal portfolio liquidation under market impact. The coefficients can be random in which case the value function is described by a degenerate backward stochastic partial differential equation (BSPDE) with singula…
Framework uses deep learning and statistical models to solve PDEs with discontinuous coefficients.
problem Solving PDEs with discontinuous coefficients.
method Two-stage physics-informed deep learning and statistical mixture models.
result Framework achieves adaptability and accurate parameter identification.
The paper uses Floer homology to study twist coefficients and their behavior after capping off.
problem Behavior of twist coefficients after capping off a boundary component.
method Heegaard Floer homology to constrain twist coefficients.
result Results about fractional Dehn twists and Floer homology of cyclic branched covers.
The paper solves MMV and MV problems with random coefficients and finds shared optimal strategies.
problem Optimal trading strategies with random market coefficients.
method Backward stochastic differential equations (BSDEs) to find optimal strategies.
result MMV and MV problems share the same optimal portfolio and value under random coefficients.
A new method clusters multi-view data by sharing a common trace-norm of coefficient matrices.
problem Insufficient exploitation of multi-view data due to uniform coefficient matrices.
method Imposes bilinear factorization with orthonormality and low-rank constraints on coefficient matrices.
result The proposed CBF-MSC method effectively clusters multi-view data more comprehensively.
Study optimal investment and reinsurance strategy for insurers under random coefficients.
problem Optimal mean-variance investment-reinsurance problem for insurers under Cramér-Lundberg model with random coefficients.
method Reduced to a constrained stochastic linear-quadratic control problem with jumps, solved using BSDE techniques and SREs.
result Explicit efficient investment-reinsurance strategy and mean-variance frontier.
Efficient method solves constrained Lasso problems.
problem Variable selection with prior information.
method Inexact augmented Lagrangian method exploiting second-order sparsity.
result Superior performance compared to first-order methods.
New algorithm solves utility maximization with deep learning for constrained problems.
problem Maximizing utility under convex constraints with random coefficients.
method Developed a new algorithm using stochastic maximum principle and deep learning.
result The new algorithm outperforms existing methods in accuracy and applicability.
New MMM captures hierarchical marketing effects and sign restrictions.
problem Measuring effectiveness of marketing activities with hierarchical structure and sign constraints.
method Proposes a constrained maximum likelihood approach using Hamiltonian Monte Carlo algorithm.
result Demonstrates superior performance on real datasets compared to multi-stage methods.
Analytic networks with bounded coefficients can't outperform polynomial approximations.
problem Approximation limits of neural networks with analytic activation functions under coefficient constraints.
method Deterministic analysis using comparison argument and Bernstein-type estimates.
result Networks with analytic activation functions and controlled coefficients cannot outperform classical polynomial approximation rates on non-analytic targets.
We investigate the ergodic problem of growth-rate maximization under a class of risk constraints in the context of incomplete, Itô-process models of financial markets with random ergodic coefficients. Including {\em value-at-risk} (VaR), {\em tail-value-at-risk} (TVaR), and {\em limited expected loss} (LEL), these cons…
DS2CF-Net learns hierarchical representations with deep coupled factorization and enriched prior.
problem Learning deep hierarchical representations from data.
method Dual-constrained Deep Semi-Supervised Coupled Factorization Network (DS2CF-Net) with enriched prior.
result DS2CF-Net achieves state-of-the-art performance in representation learning and clustering.
Study gauged supergravity, M5-branes, and class R theories, constraining supergravity coefficients and calculating partition functions.
problem Constraints and calculations in higher-derivative supergravity and related theories.
method Holography, Chern-Simons theory, 3d-3d correspondence, wrapped M5-branes.
result Constrained coefficients in supergravity Lagrangian, calculated partition functions for class R theories.
The fused lasso is analyzed for high-dimensional piecewise-constant regression coefficients.
problem Estimation of high-dimensional piecewise-constant regression coefficients.
method Formulated a restricted isometry condition for the fused lasso estimator and derived estimation bounds.
result The estimation error can be dominated by either the lasso or the fused lasso rate, depending on the number of non-zero coefficients and piece-wise constant segments.
The non-negative solution to an underdetermined linear system can be uniquely recovered sometimes, even without imposing any additional sparsity constraints. In this paper, we derive conditions under which a unique non-negative solution for such a system can exist, based on the theory of polytopes. Furthermore, we deve…
c-lasso is a Python tool for robust and sparse regression with linear constraints.
problem Sparse and robust linear regression with linear constraints.
method Estimates coefficients and scale under linear constraints using perspective M-estimators.
result Provides estimators for various loss functions with linear constraints.
Paper sets fundamental limits for distributed covariance estimation with constrained communication.
problem Estimating high-dimensional covariance matrices in a feature-split setting with limited communication.
method Developed a Conditional Strong Data Processing Inequality (C-SDPI) to establish minimax lower bounds and an optimal estimation protocol.
result Achieved nearly optimal estimation protocol with sample and communication requirements matching lower bounds up to logarithmic factors.
New method improves DAG learning by using large coefficients for higher-order terms.
problem Recovering DAG structures from observational data is challenging due to combinatorial optimization.
method Proposes truncated matrix power iteration to approximate DAG constraints efficiently.
result Empirically outperforms previous methods by a factor of 3 or more in structural Hamming distance.
Study optimal investment-reinsurance strategy for insurers under random coefficients and jumps.
problem Optimal investment-reinsurance strategy for insurers with random coefficients and jumps.
method Solves backward stochastic differential equations with jumps under a convex cone constraint.
result Optimal strategy and value remain the same even with random coefficients and jumps.
We consider regression scenarios where it is natural to impose an order constraint on the coefficients. We propose an order-constrained version of L1-regularized regression for this problem, and show how to solve it efficiently using the well-known Pool Adjacent Violators Algorithm as its proximal operator. The main ap…
Invariants measure letter interleaving in groups, detecting group dimensions.
problem Detecting group dimensions in arbitrary groups.
method Defining letter-braiding invariants from cochain models of spaces with prescribed fundamental groups.
result Letter-braiding invariants are complete invariants of group dimension series.
We study Eγ-divergence contraction and its privacy implications.
problem Analyzing privacy in data processing and algorithms.
method Generalizing Dobrushin's coefficient to Eγ-divergence and deriving contraction coefficients. result Local differential privacy can be expressed in terms of Eγ-divergence contraction, leading to precise sample size reductions. New bounds for γ-regret using modified Decision-Estimation Coefficient.
problem Statistical characterization of γ-regret for complex bandit problems. method Statistical characterization via γ-DEC, a modified Decision-Estimation Coefficient. result Upper and lower bounds for γ-regret nearly match, showing fundamental limits. Novel method estimates complex nonlinear systems with stochastic differential equations.
problem Handling complex nonlinear dynamical systems with strong learning guarantees.
method Estimates drift and diffusion coefficients of continuous, multidimensional, nonlinear controlled stochastic differential equations.
result Strong theoretical guarantees including finite-sample bounds for various metrics.
The Markowitz problem consists of finding in a financial market a self-financing trading strategy whose final wealth has maximal mean and minimal variance. We study this in continuous time in a general semimartingale model and under cone constraints: Trading strategies must take values in a (possibly random and time-de…
A new method solves complex control problems with random coefficients.
problem Solving LQ McKean-Vlasov control problems with random coefficients.
method Decomposes the problem into two decoupled stochastic optimal control problems.
result The sum of optimal controls of auxiliary problems equals the original problem's optimal control.
Investor optimizes investment and consumption under uncertain market conditions with constraints.
problem Investor optimizes investment and consumption in a stochastic environment with model uncertainty and constraints.
method Robust control problem solved using stochastic Hamilton-Jacobi-Bellman-Isaacs equations, backward stochastic differential equations, and bounded mean oscillation martingale theory.
result Investor incurs utility loss when ignoring model uncertainty, and constraints impact optimal strategy and value function.
The paper tackles online resource allocation with uncertain coefficients and chance constraints.
problem Online stochastic resource allocation problem with chance constraints.
method Linearization and primal-dual algorithms with heuristic corrections.
result Optimality gap and constraint violation are on the order of √n.
The principle of absence of arbitrage opportunities allows obtaining the distribution of stock price fluctuations by maximizing its information entropy. This leads to a physical description of the underlying dynamics as a random walk characterized by a stochastic diffusion coefficient and constrained to a given value o…
New DEC variant improves sample complexity bounds in decision making.
problem Understanding sample-efficient learning guarantees in decision making.
method Introducing a new Constrained Decision-Estimation Coefficient (DEC) and using it to derive improved lower bounds.
result New lower bounds improve upon prior work in three aspects: expectation, global applicability, and improper reference models.
Forward stagewise regression follows a very simple strategy for constructing a sequence of sparse regression estimates: it starts with all coefficients equal to zero, and iteratively updates the coefficient (by a small amount ε) of the variable that achieves the maximal absolute inner product with the current residua…
Identifying homogeneous subgroups of variables can be challenging in high dimensional data analysis with highly correlated predictors. We propose a new method called Hexagonal Operator for Regression with Shrinkage and Equality Selection, HORSES for short, that simultaneously selects positively correlated variables and…
MOMENT selects and estimates mixed-effects models using moment identities.
problem Selecting and estimating random-effects covariance matrix and fixed-effects coefficients in multiresponse linear mixed-effects models.
method MOMENT is a stage-wise moment-based framework that reduces the random-effects selection problem to a smooth constrained convex optimization problem.
result MOMENT performs competitively and can outperform separate univariate analyses for correlated responses.
High-dimensional data often lie in low-dimensional subspaces corresponding to different classes they belong to. Finding sparse representations of data points in a dictionary built using the collection of data helps to uncover low-dimensional subspaces and address problems such as clustering, classification, subset sele…
Study S-shaped utility maximization with VaR constraint and unobservable drift.
problem Maximizing utility with a Value at Risk (VaR) constraint and unknown drift.
method Bayesian filter, concavification principle, change of measure, semi-closed integral representation, algorithms (Lagrange, simulation, deep neural network).
result Critical wealth level determining solution feasibility and optimal solution existence.
Study reveals structural constraints on income inequality in Latin America.
problem Income inequality in Latin America compared to other economies.
method Product space, Product Gini Index, Xgini coefficient.
result LAC economies are more dependent on products related to high income inequality.
KReTTaH uses tensor trains and Hadamard overparameterization for fast, interpretable multi-way data imputation.
problem Multi-way data imputation for high-dimensional functional MRI and dynamic graph recovery.
method Reformulates imputation as RKHS regression with TT-constrained coefficients and Hadamard overparameterization. Optimizes TT coefficients and kernel matrices on Riemannian manifolds.
result Consistently outperforms state-of-the-art methods in modeling accuracy.
KReTTaH uses tensor trains and Hadamard overparameterization for fast, interpretable multi-way data imputation.
problem Multi-way data imputation in high-dimensional spaces.
method Reformulates imputation as RKHS regression with TT-constrained coefficients, optimized on manifold frameworks.
result Consistently outperforms state-of-the-art methods in accuracy.
A new estimator learns sparse linear models with context-dependent coefficients.
problem Sparse linear models lack flexibility compared to deep neural networks for handling feature groups.
method Contextual lasso estimator using a deep neural network with lasso regularization.
result Learned models can be sparser than standard lasso without sacrificing predictive power.
Sparse linear regression, which entails finding a sparse solution to an underdetermined system of linear equations, can formally be expressed as an l0-constrained least-squares problem. The Orthogonal Least-Squares (OLS) algorithm sequentially selects the features (i.e., columns of the coefficient matrix) to greedil…
Optimizes material distribution on surfaces using topological derivatives.
problem Optimal distribution of two materials on smooth submanifolds in Rd. method Topological derivative approach for shape optimization constrained by PDEs.
result Numerical solution of topology optimization problem on surfaces.
Proposes a parsimonious graph spectral method for time series data.
problem Efficiently transmitting multivariate time series data.
method Graph spectral embedding with unsupervised, parsimonious encoding.
result Near-linear computational complexity and interpretable event structure.
In many applications one may acquire a composition of several signals that may be corrupted by noise, and it is a challenging problem to reliably separate the components from one another without sacrificing significant details. Adding to the challenge, in a compressive sensing framework, one is given only an undersampl…
T-Basis represents neural network tensors with fewer parameters.
problem Efficiently representing neural network tensors with fewer parameters.
method T-Basis uses Tensor Rings to represent tensors in a neural network, parameterizing them with a small number of coefficients.
result T-Basis achieves high compression rates with minimal performance loss.
This paper studies simultaneous feature selection and extraction in supervised and unsupervised learning. We propose and investigate selective reduced rank regression for constructing optimal explanatory factors from a parsimonious subset of input features. The proposed estimators enjoy sharp oracle inequalities, and w…
Paper studies quantized LRMR with random dithering for correlated tasks.
problem Estimating coefficient matrix in quantized multivariate regression.
method Uniform quantization with random dithering, constrained and regularized Lasso estimators.
result Achieves minimax optimal rate with dithering, slightly worsens quantization effect.
In this paper we study a continuous-time stochastic linear quadratic control problem arising from mathematical finance. We model the asset dynamics with random market coefficients and portfolio strategies with convex constraints. Following the convex duality approach, we show that the necessary and sufficient optimalit…