Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,786 papers · 148 categories

Trend · papers per month

1.3%2.5%3.8%5.1% · May 202619922001200920172026
48 results for Reward Penalization

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.

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.

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 ΦΦ-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…

2016-11-03abs ↗pdf ↗

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.

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…

2015-07-01abs ↗pdf ↗

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.

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.

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…

2012-11-02abs ↗pdf ↗

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…

2019-06-05abs ↗pdf ↗

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 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 \(\hatλ \simeq 0.70107\).

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.

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 λλ 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, …

2018-12-13abs ↗pdf ↗

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.