Equivalence found between algorithmic regularization and convex penalization for convex losses.
problem Understanding the relationship between algorithmic regularization and convex penalization.
method Introducing a geometric condition and showing equivalence through optimization paths.
result Optimization paths of iterative algorithms on unregularized problems match those of corresponding penalized problems under certain conditions.
The study optimizes portfolios under transaction costs and model uncertainty, showing the effectiveness of turnover penalization.
problem Optimizing portfolios under transaction costs and model uncertainty.
method Theoretical and empirical analysis linking turnover penalization to covariance shrinkage, incorporating transaction costs and parameter uncertainty.
result Turnover penalization is more effective than shrinkage methods in constructing well-performing portfolios.
Paper develops a new method for optimal stopping in American options.
problem Optimal stopping in American options with singular generators.
method Entropy-regularized penalization scheme for reflected BSDEs with singular generators.
result Limit of the penalization scheme solves a reflected BSDE with a logarithmically singular generator.
Paper uses neural networks to solve complex transport problems.
problem Optimal transport and related hedging problems.
method Penalization and neural networks to solve optimization problems.
result Effective solution to multi-marginal, martingale optimal transport problems.
CD converges linearly for MCP/SCAD penalized least squares.
problem Recovering sparse signals from data.
method Coordinate descent for MCP/SCAD penalized least squares.
result CD converges linearly to solutions of MCP/SCAD penalized least squares.
Improved asset allocation strategies using penalized quantile regression.
problem Improving investment strategies in asset allocation.
method Post-penalization, nonconvex penalties, and optimal tuning parameter selection.
result Alternative methods outperform simple LASSO, especially for extreme risk.
Improved DPO framework penalizes preference uncertainty to avoid overoptimization.
problem Aligning LLMs to human preferences is challenging due to varied, context-dependent, and ambiguous preferences.
method Developed a pessimistic framework for DPO by introducing preference uncertainty penalization schemes.
result Improved overall performance and better completions on high-uncertainty responses compared to vanilla DPO.
This paper introduces a gradient analysis framework to improve language model performance by rewarding good examples and penalizing bad ones.
problem Improving language model output quality by penalizing bad examples.
method Gradient analysis of loss functions to reward good examples and penalize bad ones.
result ExMATE is superior to MLE and combining DPO with ExMATE enhances performance.
New proof shows entropic penalization converges exponentially fast.
problem Analyzing convergence of entropic penalization in linear programs.
method Non-asymptotic proof with explicit constants.
result Entropic penalization converges exponentially fast for any linear program.
Study nonparametric density estimation via measure transport, achieving optimal rates.
problem Nonparametric density estimation with optimal rates.
method Measure transport, penalized maximum likelihood, and sieved wavelet estimators.
result Achieve minimax optimal convergence rates over Hölder classes of densities.
Study pairs trading strategy with uncertain drift and penalized risk.
problem Optimizing pairs trading strategy with uncertain drift and risk penalty.
method Model pairs trading as a Gaussian mean-reverting process with a Markov chain, use stochastic filtering theory, and solve for logarithmic utility function.
result Characterize optimal strategies and value functions under full and partial information, showing certainty equivalence principle.
This paper optimizes portfolio selection by penalizing tracking error, improving Sharpe ratio.
problem Optimizing portfolio allocation with a penalty for deviation from a reference portfolio.
method Formulated as a McKean-Vlasov control problem, provides explicit solutions and asymptotic expansions.
result The penalized portfolio strategy outperforms standard mean-variance and reference portfolios in most cases.
Paper reformulates UOT as non-negative penalized linear regression for efficient algorithms.
problem Optimal transport with relaxed marginal conditions.
method Reformulate UOT as non-negative penalized linear regression, propose multiplicative updates.
result Efficient algorithms for UOT with quadratic penalties, continuity of solutions.
The paper tackles pricing vulnerable options via generalized BSDEs and penalization schemes.
problem Pricing options in a general hazard process setup.
method Establishes well-posedness and comparison theorems for generalized BSDEs and RBSDEs, studies penalization schemes.
result Well-posedness results and comparison theorems for generalized BSDEs and RBSDEs, extended penalization schemes.
In this paper, we propose a one-pass algorithm on MapReduce for penalized linear regression \[f_λ(α, β) = \|Y - α\mathbf{1} - Xβ\|_2^2 + p_λ(β)\] where α is the intercept which can be omitted depending on application; β is the coefficients and pλ is the penalized function with penalizing parameter λ. $f_λ(α, β…
New method improves feature selection in tree-based models.
problem Previous feature selection methods in tree-based models lack sufficient regularization and sub-optimal performance.
method Developed a new gain penalization approach for tree-based models that allows for flexible feature-specific importance weights.
result The new method improves out-of-sample performance, especially with correlated features.
Data-driven optimization improves mean-variance portfolios by penalizing norms.
problem Estimation error in mean-variance optimization.
method Augment MVO with norm penalties, use neural networks for optimization, and compute derivatives implicitly.
result Data-driven optimization reduces portfolio risk compared to standard MVO.
New insights into balancing reward and fairness in stochastic MAB.
problem Balancing reward and fairness in stochastic multi-armed bandits.
method Formulated a penalization framework and proposed a hard-threshold UCB-like algorithm.
result Asymptotic fairness, nearly optimal regret, better reward-fairness tradeoff.
We propose a new sparsity-smoothness penalty for high-dimensional generalized additive models. The combination of sparsity and smoothness is crucial for mathematical theory as well as performance for finite-sample data. We present a computationally efficient algorithm, with provable numerical convergence properties, fo…
Paper proposes a new method to optimize deep neural networks with sparse regularization.
problem Difficulty in achieving optimal convergence rates for deep neural networks due to sparsity constraints.
method Introduces a novel penalized estimation method for sparse DNNs, resolving computational and theoretical issues.
result Establishes an oracle inequality for the excess risk of the proposed sparse-penalized DNN estimator and derives convergence rates.
Study optimizes portfolio to minimize relative drawdown duration, penalizing unfavorable performance states.
problem Minimizing relative drawdown duration in portfolio optimization relative to a benchmark.
method Introduces a benchmark-relative drawdown-duration criterion penalizing unfavorable performance states. Uses a one-dimensional Markovian representation and Hamilton-Jacobi-Bellman equation.
result Derives explicit projection-based characterization of the optimal feedback control and identifies geometric settings for unique strong solutions.
The paper develops adaptive deep learning methods for nonlinear time series models.
problem Estimating mean functions of non-stationary and nonlinear time series models.
method Develops non-penalized and sparse-penalized DNN estimators for general non-stationary time series, derives minimax lower bounds, and shows the sparse-penalized DNN estimator is adaptive and optimal.
result Sparse-penalized DNN estimator achieves minimax optimal rates for many nonlinear AR models.
The MM algorithm improves robust penalized estimation for outlier-contaminated data.
problem Outliers in data affect the reliability of penalized estimation.
method Innovative MM algorithm for both convex and nonconvex loss functions.
result Established convergence theory for MM algorithm with various loss functions.
A new method for nonparametric regression using mesh-based solutions.
problem Estimating regression functions non-parametrically with computational tractability.
method Mesh-based approximate solution (MBS) for penalized regression problems.
result MBS transforms NPR to a discrete convex minimization problem, making it computationally feasible.
We introduce a recursive adaptive group lasso algorithm for real-time penalized least squares prediction that produces a time sequence of optimal sparse predictor coefficient vectors. At each time index the proposed algorithm computes an exact update of the optimal ℓ1,∞-penalized recursive least squares (R…
Folded concave penalization methods have been shown to enjoy the strong oracle property for high-dimensional sparse estimation. However, a folded concave penalization problem usually has multiple local solutions and the oracle property is established only for one of the unknown local solutions. A challenging fundamenta…
XCAN uses cross-product penalization for sparse matrix factorization.
problem Understanding complex data structures.
method Sparse matrix factorization with a loss function balancing variance and structural preservation.
result Flexible modeling approach for diverse applications.
A new Branch-and-Bound solver tackles L0-penalized problems with flexible loss functions.
problem Solving L0-penalized optimization problems with a broader class of loss functions.
method Generic Branch-and-Bound procedure with closed-form expressions for key quantities.
result El0ps solver achieves state-of-the-art performance and extends computational feasibility.
New algorithms find optimal policies without knowing MDP span.
problem Finding optimal policies in MDPs without knowing span.
method Horizon calibration and span penalization techniques.
result First algorithms achieving optimal span-based complexity without prior knowledge.
Developed a new algorithm to improve dynamic treatment regimens.
problem Non-convergence of Q-learning-based Q-shared algorithm in dynamic treatment regimens.
method Penalized Q-shared algorithm to address convergence issues.
result The penalized Q-shared algorithm converges and outperforms the original in various settings.
Unified framework for pattern recovery in penalized and thresholded estimation.
problem Pattern recovery in penalized and thresholded estimation methods.
method Defining a novel pattern notion based on subdifferentials, introducing accessibility and noiseless recovery conditions.
result Unified and extended conditions for pattern recovery in a broad class of penalized estimators.
Mol-CycleGAN generates optimized molecules with similar structure.
problem Designing molecules with desired properties is challenging.
method CycleGAN-based model that generates optimized compounds with high structural similarity.
result Significantly outperforms previous results in optimizing penalized logP of drug-like molecules.
Dimension reduction and variable selection are performed routinely in case-control studies, but the literature on the theoretical aspects of the resulting estimates is scarce. We bring our contribution to this literature by studying estimators obtained via L1 penalized likelihood optimization. We show that the optimize…
Proposes a method to classify with matrix-valued predictors using penalized likelihood.
problem Classification with matrix-valued predictors.
method Penalized likelihood method with Kronecker product decomposition for precision matrix estimation.
result Outperforms competitors in classification accuracy, even when assumptions are violated.
Paper estimates differences in multi-attribute Gaussian graphical models using non-convex penalties.
problem Estimating differences in multi-attribute Gaussian graphical models with similar structure.
method Penalized D-trace loss function with non-convex (log-sum and SCAD) penalties, proximal gradient descent methods.
result Theoretical analysis and numerical examples support consistency in support recovery and estimation.
We present an approach for penalized tensor decomposition (PTD) that estimates smoothly varying latent factors in multi-way data. This generalizes existing work on sparse tensor decomposition and penalized matrix decompositions, in a manner parallel to the generalized lasso for regression and smoothing problems. Our ap…
Flexible empirical Bayes for large-scale multiple linear regression.
problem Large-scale multiple linear regression with flexible priors and efficient computation.
method Adaptive shrinkage priors combined with variational approximations for hyperparameter estimation.
result The posterior mean from the empirical Bayes method solves a penalized regression problem.
The paper tackles deep learning from dependent data, achieving optimal performance.
problem Deep learning from strongly mixing observations, especially with regularization and optimality.
method Sparse-penalized regularization for deep neural networks, oracle inequality for expected excess risk.
result Deep neural network estimator achieves minimax optimal rate for nonparametric autoregression.
The paper develops robust risk measures for uncertain loss positions.
problem Risk assessment for loss positions with uncertain distributions.
method Robust optimized certainty equivalents and generalized quantiles are proposed and analyzed.
result Robust expectiles with specific penalization functions are coherent risk measures.
Optimizes biomarker selection for cost-effective treatment rules.
problem Incorporating multiple biomarkers in treatment selection rules can be costly and reduce model performance.
method Developed procedures for estimating linear and nonlinear combinations of biomarkers using 0-norm penalized weighted classification.
result Demonstrated the importance of feature selection and marker cost in treatment selection rules.
We propose a general technique for improving alternating optimization (AO) of nonconvex functions. Starting from the solution given by AO, we conduct another sequence of searches over subspaces that are both meaningful to the optimization problem at hand and different from those used by AO. To demonstrate the utility o…
POTNet uses penalized optimal transport to generate data without mode collapse.
problem Mode collapse in WGANs leading to poor synthetic data generation.
method POTNet employs marginally-penalized Wasserstein distance for deep generative modeling.
result POTNet effectively captures underlying data structures, including tail behaviors and minor modalities.
Develops flexible algorithms for estimating heterogeneous treatment effects.
problem Flexible estimation of heterogeneous treatment effects in observational studies.
method Two-step algorithm: 1) Estimate marginal effects and treatment propensities, 2) Optimize data-adaptive objective function.
result Achieves quasi-oracle property, leading to error bounds similar to an oracle.
Let $\cF$ be a set of M classification procedures with values in [−1,1]. Given a loss function, we want to construct a procedure which mimics at the best possible rate the best procedure in $\cF$. This fastest rate is called optimal rate of aggregation. Considering a continuous scale of loss functions with various …
The paper optimizes bridge-type estimators for sparse models using pathwise methods.
problem Sparse parametric models with adaptive coefficients and multiple penalties.
method Pathwise optimization with accelerated proximal gradient descent and blockwise alternating optimization.
result Efficient computation of the full solution path for adaptive bridge estimators.
Develops a new duality between entropy martingale optimal transport and nonlinear pricing-hedging.
problem Entropy Martingale Optimal Transport problem and its associated optimization problem.
method Combines Entropy Optimal Transport and Martingale Optimal Transport theories, with novel penalization terms and constraints.
result Establishes a nonlinear robust pricing-hedging duality, covering various known robust results.
New algorithm improves GAIL for image sequences with global encoder and reward penalization.
problem Low-level, high-dimensional state input in GAIL framework.
method Global encoder and reward penalization mechanism.
result Significant performance improvement in low-level and high-dimensional tasks.
A l1-norm penalized orthogonal forward regression (l1-POFR) algorithm is proposed based on the concept of leaveone- out mean square error (LOOMSE). Firstly, a new l1-norm penalized cost function is defined in the constructed orthogonal space, and each orthogonal basis is associated with an individually tunable regulari…