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.
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 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.
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.
GRPO optimizes LLMs with verifiable rewards, amplifying policy success.
problem Improving LLMs' reasoning under verifiable binary rewards.
method Introduces GRPO, analyzes variants of reward normalization and regularization.
result GRPO amplifies policy success, converging to a fixed point exceeding the reference.
In this paper, we introduce a novel combined reward cum penalty loss function to handle the regression problem. The proposed combined reward cum penalty loss function penalizes the data points which lie outside the ε-tube of the regressor and also assigns reward for the data points which lie inside of the ε-tube of…
SPARKLE handles high-dimensional covariates for online decision-making.
problem Complex reward-covariate relationships in high-dimensional settings.
method SPARKLE uses a sparse additive reward model with doubly penalized estimator and adaptive screening.
result SPARKLE achieves sublinear regret bound logarithmic in covariate dimensionality.
A new method for reinforcement learning that adapts to different domains using auxiliary classifiers.
problem Training reinforcement learning agents to perform well in different domains with varying dynamics.
method Learning auxiliary classifiers to distinguish source-domain from target-domain transitions and modifying the reward function accordingly.
result The approach improves transfer performance in reinforcement learning tasks with varying dynamics.
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.
BRAID fine-tunes diffusion models to optimize reward models in offline scenarios.
problem Combining generative modeling and model-based optimization in offline scenarios.
method Conservative fine-tuning of diffusion models using RL to optimize reward models.
result BRAID outperforms existing methods in offline data, avoiding invalid designs.
Develops statistical framework for resolving reward function ambiguity in inverse reinforcement learning.
problem Non-uniqueness of reward functions in inverse reinforcement learning.
method Entropy regularization combined with least-squares reconstruction of the reward from the soft Bellman residual.
result Least-squares reward function is unique and consistent with the expert policy.
Paper robustifies reinforcement learning with risk-averse methods.
problem Making predictions robust to changes in system dynamics or rewards.
method Approximates Robust Reinforcement Learning using Φ-divergence and Risk-Averse formulation. result Classical Reinforcement Learning can be robustified using standard deviation penalization.
Many practical environments contain catastrophic states that an optimal agent would visit infrequently or never. Even on toy problems, Deep Reinforcement Learning (DRL) agents tend to periodically revisit these states upon forgetting their existence under a new policy. We introduce intrinsic fear (IF), a learned reward…
New scoring rules improve probabilistic classification model evaluation.
problem Traditional scoring rules misalign with the preference for correct classifications.
method Introduces Penalized Brier Score (PBS) and Penalized Logarithmic Loss (PLL) to modify proper scoring rules.
result PBS and PLL better identify optimal checkpoints and early stopping points, leading to superior F1 scores.
New method boosts skill learning by encouraging optimistic exploration.
problem Intrinsic reward for exploration is inherently pessimistic.
method Derive an information gain auxiliary objective involving an ensemble of discriminators and rewarding policy disagreement.
result Improves skill learning in grid worlds and Atari games.
AdaDEM decouples EM into two parts to improve class overlap and uncertainty.
problem Improper EM limits its effectiveness in various machine learning tasks.
method Decouple EM into CADF and GMC, and AdaDEM normalizes CADF reward and uses MEC.
result AdaDEM outperforms classical EM and improves performance in noisy and dynamic environments.
It is well known that quantile regression model minimizes the portfolio extreme risk, whenever the attention is placed on the estimation of the response variable left quantiles. We show that, by considering the entire conditional distribution of the dependent variable, it is possible to optimize different risk and perf…
AOT aligns LLMs on distributional preferences via optimal transport.
problem Current LLM alignment techniques lack distributional level alignment.
method Alignment via Optimal Transport (AOT) aligns LLMs on unpaired preference data.
result AOT enables alignment by penalizing reward distribution violations.
New exploration bonuses improve reinforcement learning efficiency.
problem Efficient exploration in unknown environments with limited feedback.
method Improved exploration bonuses scaling with 1/n and improved stopping time analysis.
result Faster learning rates and improved sample complexity in pure-exploration settings.
We tackle the blackbox issue of deep neural networks in the settings of reinforcement learning (RL) where neural agents learn towards maximizing reward gains in an uncontrollable way. Such learning approach is risky when the interacting environment includes an expanse of state space because it is then almost impossible…
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.
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.
AgFlow speeds up model selection in penalized PCA.
problem Efficient model selection in penalized PCA for HDLSS settings.
method Implicit regularization effect of gradient flow to reduce computation complexity.
result AgFlow achieves the complete solution path of L2-penalized PCA.
We consider the Willmore functional on graphs, with an additional penalization of the area where the curvature is non-zero. Interpreting the penalization parameter as a Lagrange multiplier, this corresponds to the Willmore functional with a constraint on the area where the graph is flat. Sending the penalization parame…
New metrics CWSA and CWSA+ improve model evaluation under confidence thresholds.
problem Lack of metrics capturing model reliability under confidence thresholds.
method Introducing CWSA and CWSA+ metrics that reward confident accuracy and penalize overconfident mistakes.
result CWSA and CWSA+ outperform classical metrics in trust-sensitive tests.
Develops a method to predict stock returns with time-varying risk premia.
problem Predicting stock returns with time-varying risk premia while maintaining no-arbitrage restrictions.
method Penalized two-pass regression with time-varying factor loadings, incorporating penalization in the first pass and grouping in the second pass.
result The proposed method reduces prediction errors compared to other approaches.
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.
This paper shows RL with KL penalties is equivalent to Bayesian inference for fine-tuning LMs.
problem Fine-tuning large language models to avoid undesirable features.
method Analyzed KL-regularized RL and showed it's equivalent to variational inference.
result KL-regularized RL avoids distribution collapse and is more insightful as Bayesian inference.
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.
In high-dimensional data analysis, penalized likelihood estimators are shown to provide superior results in both variable selection and parameter estimation. A new algorithm, APPLE, is proposed for calculating the Approximate Path for Penalized Likelihood Estimators. Both the convex penalty (such as LASSO) and the nonc…
We present an approach to make molecular optimization more efficient. We infer a hypergraph replacement grammar from the ChEMBL database, count the frequencies of particular rules being used to expand particular nonterminals in other rules, and use these as conditional priors for the policy model. Simulating random mol…
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…
Portfolio management problems are often divided into two types: active and passive, where the objective is to outperform and track a preselected benchmark, respectively. Here, we formulate and solve a dynamic asset allocation problem that combines these two objectives in a unified framework. We look to maximize the exp…
No communication allows optimal instance-dependent regret guarantees in multi-player bandits.
problem Achieving optimal instance-dependent regret in multi-player multi-armed bandits without communication.
method Characterization of Pareto optimal trade-offs and development of an algorithm.
result Achieving optimal instance-dependent regret requires strict sub-optimality in other regimes.
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.
The paper classifies and analyzes the stability of elastic curves with fixed endpoints.
problem Classification and stability of pinned elasticae.
method Critical points of the length-penalized elastic bending energy among planar curves with fixed endpoints.
result Explicit parametrization and classification of all critical points with a threshold parameter \(\hatλ \simeq 0.70107\).
We extend the analysis of investment strategies derived from penalized quantile regression models, introducing alternative approaches to improve state\textendash of\textendash art asset allocation rules. First, we use a post\textendash penalization procedure to deal with overshrinking and concentration issues. Second, …
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.
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.
In this paper, we study the performance of extremum estimators from the perspective of generalization ability (GA): the ability of a model to predict outcomes in new samples from the same population. By adapting the classical concentration inequalities, we derive upper bounds on the empirical out-of-sample prediction e…
In this paper we purpose a blockwise descent algorithm for group-penalized multiresponse regression. Using a quasi-newton framework we extend this to group-penalized multinomial regression. We give a publicly available implementation for these in R, and compare the speed of this algorithm to a competing algorithm --- w…
Proposes a new robust expectile regression method for high-dimensional data.
problem Heterogeneity in high-dimensional data with heteroscedastic variance or inhomogeneous covariate effects.
method Iteratively reweighted ℓ1-penalization for robust expectile regression (retire).
result Oracle convergence rate after log(log d) iterations in high-dimensional settings.
Study on elastic curves pinned at the boundary, focusing on minimizers and their interaction with obstacles.
problem Minimizing elastic bending energy for open planar curves with obstacles.
method Investigation of global minimizers and explicit solutions for different values of the penalization parameter.
result Explicit threshold for λ above which minimizers touch the obstacle, regardless of obstacle shape. We prove that L2-Boosting lacks a theoretical property which is central to the behaviour of l1-penalized methods such as basis pursuit and the Lasso: Whereas l1-penalized methods are guaranteed to recover the sparse parameter vector in a high-dimensional linear model under an appropriate restricted nullspace property, …
MOPO optimizes offline RL by penalizing dynamics uncertainty.
problem Learning policies from offline data with distributional shift.
method Modify model-based RL to avoid distributional shift.
result MOPO outperforms model-free and standard model-based RL.
New methods correct spectral distortions using known analyte concentrations.
problem Distorted spectral shapes from absorbing and scattering contributions.
method Modified penalized baseline correction methods that incorporate known analyte concentrations.
result Improved prediction performance on near infra-red data sets.
A new robust regression method handles outliers in high-dimensional data.
problem Outliers in high-dimensional data make conventional regression methods ineffective.
method Robust penalized least squares of depth trimmed residuals regression.
result The new method outperforms existing methods in estimation and prediction accuracy.
Algorithm samples from Wasserstein barycenter of measures.
problem Sampling from Wasserstein barycenter of measures.
method Gradient flow of multimarginal formulation with penalization.
result Algorithm samples close to Wasserstein barycenter.