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.

168,742 papers · 148 categories

Trend · papers per month

count % of corpus

48 results for “stepwise lookahead”

Uncovering Feature Interdependencies in High-Noise Environments with Stepwise Lookahead Decision Forestscs.LG

A new random forest algorithm uncovers feature interdependencies better than traditional methods.

problem Tackles the sub-optimality of greedy decision tree implementations in random forests.

method Presented a 'stepwise lookahead' variation of random forests that considers multiple split nodes simultaneously.

result Significantly outperforms greedy random forests in uncovering feature interdependencies, especially in high-noise environments.

feature interdependencies random forests stepwise lookahead greedy algorithms high-noise environments

2020-09-30abs ↗pdf ↗

Reinforcement Learning with Lookahead Informationcs.LG

New RL algorithms use lookahead info to maximize rewards.

problem RL in unknown environments without lookahead info.

method Planning using empirical reward and transition distributions.

result Achieves tight regret compared to lookahead info.

Reinforcement Learning Lookahead Information Regret Minimization Empirical Distributions Planning Algorithms

2024-06-04abs ↗pdf ↗

Detecting Lookahead Bias in LLM Forecastsq-fin.GN

We detect lookahead bias in LLM forecasts using a novel statistical method.

problem Detecting lookahead bias in LLM-generated economic forecasts.

method Developed a statistical procedure using date-only recall queries and estimated Lookahead Propensity (LAP).

result LLM forecasts are contaminated with lookahead bias, as indicated by a positive interaction between LAP and the forecast in accuracy regressions.

LLM forecasts lookahead bias statistical procedure date-only recall Lookahead Propensity (LAP)

2025-12-29abs ↗pdf ↗

Reinforcement Learning with Multi-Step Lookahead Information Via Adaptive Batchingcs.LG

New algorithm learns optimal policy with multi-step lookahead information.

problem Learning optimal policy in reinforcement learning with multi-step lookahead information is NP-hard.

method Adaptive batching policies that process lookahead in state-dependent chunks.

result Order-optimal regret bounds up to a constant factor of lookahead horizon.

Reinforcement Learning Multi-step Lookahead Adaptive Batching Optimal Policy Regret Minimization

2026-01-15abs ↗pdf ↗

Lookahead: A Far-Sighted Alternative of Magnitude-based Pruningcs.LG

Lookahead pruning extends single-layer optimization to multi-layer, outperforming magnitude-based pruning.

problem Pruning neural networks to reduce computational cost and memory usage.

method Developed a multi-layer optimization approach extending the single-layer optimization of magnitude-based pruning.

result Consistently outperforms magnitude-based pruning on various networks, especially in high sparsity.

neural networks pruning magnitude-based pruning lookahead pruning Frobenius distortion

2020-02-12abs ↗pdf ↗

Fast Non-Episodic Finite-Horizon RL with K-Step Lookahead Thresholdingcs.LG

New RL method learns K-step lookahead Q-functions for fixed-horizon MDPs.

problem Challenges in online reinforcement learning for non-episodic, finite-horizon MDPs.

method Introduces a K-step lookahead Q-function with a time-varying threshold for selecting actions.

result Achieves minimax optimal constant regret for K=1 and

\mathcal{O}(\max((K-1),C_{K-1})\sqrt{SAT\log(T)})

regret for K ≥ 2.

reinforcement learning finite horizon lookahead Q-function thresholding tabular learning

2026-01-31abs ↗pdf ↗

Recursive Two-Step Lookahead Expected Payoff for Time-Dependent Bayesian Optimizationmath.OC

A new Bayesian method optimizes time-dependent expensive functions with lookahead.

problem Maximizing a time-dependent, expensive oracle with limited evaluations.

method Recursive, two-step lookahead expected payoff (r2LEY) acquisition function.

result r2LEY outperforms myopic methods in synthetic and real-world datasets.

Bayesian optimization time-dependent lookahead expected payoff expensive oracle

2020-06-14abs ↗pdf ↗

Generalization and Optimization of SGD with Lookaheadcs.LG

The Lookahead optimizer improves SGD's performance and generalization without restrictive assumptions.

problem Improving the generalization of SGD with Lookahead.

method A rigorous stability and generalization analysis of the Lookahead optimizer with minibatch SGD, leveraging on-average model stability.

result Derives generalization bounds for convex and strongly convex problems without the restrictive Lipschitzness assumption, demonstrating a linear speedup with batch size.

SGD Lookahead optimizer minibatch generalization stability

2025-09-19abs ↗pdf ↗

Lookahead-Bounded Q-Learningcs.LG

LBQL improves Q-learning by using lookahead bounds for better performance.

problem Improving Q-learning in stochastic environments.

method LBQL uses lookahead bounds to construct dual penalties and track upper and lower bounds via stochastic approximation.

result LBQL converges faster and is more robust to hyperparameters than standard Q-learning.

Q-learning lookahead bounds stochastic environments convergence robustness

2020-06-28abs ↗pdf ↗

Instruction Tuning Chronologically Consistent Language Modelscs.LG

New models avoid lookahead bias by training on past data only.

problem Lookahead bias in language models.

method Chronologically consistent training on data before a knowledge-cutoff date.

result Elimination of lookahead bias in predictions.

language models lookahead bias chronological training predictability

2025-10-13abs ↗pdf ↗

SplitWise Regression: Stepwise Modeling with Adaptive Dummy Encodingcs.LG

SplitWise enhances stepwise regression by adaptively encoding numeric predictors into binary features.

problem Capturing nonlinear relationships in regression models without sacrificing interpretability.

method Adaptive encoding of numeric predictors into binary features using shallow decision trees, assessed by AIC or BIC.

result Consistently produces more parsimonious and generalizable models than traditional techniques.

regression modeling stepwise regression adaptive encoding Akaike Information Criterion Bayesian Information Criterion

2025-05-21abs ↗pdf ↗

Dimension Reduction of High-Dimensional Datasets Based on Stepwise SVMstat.AP

The current study proposes a dimension reduction method, stepwise support vector machine (SVM), to reduce the dimensions of large p small n datasets. The proposed method is compared with other dimension reduction methods, namely, the Pearson product difference correlation coefficient (PCCs), recursive feature eliminati…

2017-11-09abs ↗pdf ↗

Why Non-myopic Bayesian Optimization is Promising and How Far Should We Look-ahead? A Study via Rolloutcs.LG

This study improves lookahead Bayesian optimization using rollout approximation.

problem Error propagation in lookahead Bayesian optimization due to model mis-specification.

method Proves rollout's improving nature in lookahead BO and provides guidelines for choosing the rolling horizon.

result Empirical results show rollout improves over myopic and non-myopic BO algorithms.

Bayesian optimization lookahead rollout dynamic programming model mis-specification

2019-11-04abs ↗pdf ↗

Stepwise Variational Inference with Vine Copulasstat.ML

A novel stepwise VI method using vine copulas for complex latent dependence.

problem Modeling complex latent dependence structures in probabilistic models.

method Stepwise estimation of vine copula parameters using Rényi divergence and a stopping criterion.

result Our method outperforms mean-field VI and is more parsimonious in complex applications.

vine copulas stepwise VI complex dependence probabilistic models sparse Gaussian processes

2026-03-24abs ↗pdf ↗

Lookahead Optimizer: k steps forward, 1 step backcs.LG

The vast majority of successful deep neural networks are trained using variants of stochastic gradient descent (SGD) algorithms. Recent attempts to improve SGD can be broadly categorized into two approaches: (1) adaptive learning rate schemes, such as AdaGrad and Adam, and (2) accelerated schemes, such as heavy-ball an…

2019-07-19abs ↗pdf ↗

Neurosymbolic Meta-Reinforcement Lookahead Learning Achieves Safe Self-Driving in Non-Stationary Environmentscs.RO

Study improves self-driving safety in dynamic environments.

problem Safe self-driving in non-stationary urban settings.

method Neurosymbolic Meta-Reinforcement Lookahead Learning (NUMERLA).

result Self-driving agents can adapt safely in real-time.

self-driving safety meta-reinforcement lookahead non-stationary

2023-09-05abs ↗pdf ↗

Taming GANs with Lookahead-Minmaxstat.ML

A new algorithm improves GAN training stability and performance.

problem Training GANs is difficult due to variance and rotational dynamics.

method Proposes Lookahead-Minmax algorithm for minmax optimization.

result Significant improvement in GAN performance and stability.

GANs minmax optimization Lookahead stability performance

2020-06-25abs ↗pdf ↗

NoLBERT: A No Lookahead(back) Foundational Language Modelecon.GN

NoLBERT avoids lookback and lookahead biases for better econometric inference.

problem Information leakage in language models affects econometric inference.

method Pretrained on text from 1976-1995, avoiding lookback and lookahead biases.

result NoLBERT outperforms domain-specific baselines and predicts higher profit growth.

language models econometrics timestamped innovation networks profit growth

2025-09-01abs ↗pdf ↗

Next-Depth Lookahead Treestat.ML

Improves tree model performance by considering future node splits.

problem Improving tree model performance.

method Next-Depth Lookahead Tree (NDLT) model that evaluates future node splits.

result Enhanced tree model performance.

tree model performance improvement future node splits

2025-09-18abs ↗pdf ↗

DatedGPT: Preventing Lookahead Bias in Large Language Models with Time-Aware Pretrainingcs.CL

DatedGPT prevents lookahead bias in financial forecasting models.

problem Lookahead bias in large language models trained on internet-scale data.

method Time-aware pretraining with annual data cutoffs and instruction fine-tuning.

result Models' knowledge is effectively bounded by their data cutoff year, improving forecasting validity.

lookahead bias large language models financial forecasting time-aware pretraining instruction fine-tuning

2026-03-12abs ↗pdf ↗

Sparse Bayesian Learning via Stepwise Regressioncs.LG

Proposes a new algorithm for Sparse Bayesian Learning connected to Stepwise Regression.

problem Sparse Bayesian Learning for probabilistic models.

method Coordinate ascent algorithm (RMP) for SBL, showing connection to Stepwise Regression.

result RMP's noise variance parameter limit connects to Stepwise Regression, with derived guarantees.

Sparse Bayesian Learning Stepwise Regression Relevance Matching Pursuit Forward Regression Backward Regression

2021-06-11abs ↗pdf ↗

Efficient Nonmyopic Bayesian Optimization via One-Shot Multi-Step Treescs.LG

Efficiently optimizes expensive functions with multi-step lookahead using one-shot optimization.

problem Optimizing expensive functions with long-term impacts using myopic approaches.

method Formulated as nested optimization problems within a multi-step scenario tree, optimized in one-shot fashion.

result Multi-step expected improvement is computationally tractable and outperforms existing methods.

Bayesian optimization multi-step lookahead one-shot optimization fantasization Gaussian process

2020-06-29abs ↗pdf ↗

Policy Mirror Descent with Lookaheadcs.LG

Enhances PMD with lookahead to improve RL performance.

problem Improving RL performance with greedy policies over 1-step.

method Integrates multi-step greedy policies into PMD with lookahead.

result Shows faster convergence rate for

h

-PMD.

Policy Mirror Descent Lookahead RL Convergence Rate Multi-step Greedy

2024-03-21abs ↗pdf ↗

Online Planning with Lookahead Policiescs.LG

Real Time Dynamic Programming (RTDP) is an online algorithm based on Dynamic Programming (DP) that acts by 1-step greedy planning. Unlike DP, RTDP does not require access to the entire state space, i.e., it explicitly handles the exploration. This fact makes RTDP particularly appealing when the state space is large and…

2019-09-10abs ↗pdf ↗

Stochastic Stepwise Ensembles for Variable Selectionstat.ME

In this article, we advocate the ensemble approach for variable selection. We point out that the stochastic mechanism used to generate the variable-selection ensemble (VSE) must be picked with care. We construct a VSE using a stochastic stepwise algorithm, and compare its performance with numerous state-of-the-art algo…

2010-03-30abs ↗pdf ↗

Fast Lower and Upper Estimates for the Price of Constrained Multiple Exercise American Options by Single Pass Lookahead Search and Nearest-Neighbor Martingaleq-fin.CP

This paper provides fast estimates for complex option types.

problem Estimating prices for constrained multiple exercise American options.

method Lookahead search for lower estimates and nearest-neighbor martingale for upper estimates.

result Probabilistic convergence guarantees for the algorithms.

American options swing options passport options lookahead search nearest-neighbor

2020-02-26abs ↗pdf ↗

Understanding Lookahead Dynamics Through Laplace Transformmath.OC

Transforms game optimization dynamics into frequency domain for precise hyperparameter analysis.

problem Analyzing convergence of hyperparameters in game optimization.

method Frequency-domain framework using High-Resolution Differential Equations (HRDEs) and Laplace transforms.

result Derives precise convergence criteria for the Lookahead algorithm.

Hyperparameter optimization Game optimization Laplace transforms High-Resolution Differential Equations Convergence analysis

2025-06-16abs ↗pdf ↗

Look-Ahead-Bench: a Standardized Benchmark of Look-ahead Bias in Point-in-Time LLMs for Financecs.AI

Look-Ahead-Bench evaluates financial LLMs for lookahead bias, revealing significant differences in model performance.

problem Measuring and mitigating lookahead bias in financial LLMs.

method Standardized benchmark evaluating model behavior in practical financial scenarios, analyzing performance decay across market regimes.

result Standard LLMs exhibit significant lookahead bias, while Pitinf models show improved generalization and reasoning abilities.

lookahead bias financial LLMs point-in-time models model evaluation temporal performance

2026-01-20abs ↗pdf ↗

Lookahead Counterfactual Fairnesscs.LG

Introduces lookahead counterfactual fairness to account for downstream effects of ML predictions.

problem Downstream effects of ML predictions on individuals not considered by counterfactual fairness.

method Introduces lookahead counterfactual fairness (LCF), a new fairness notion that considers future status. Proposes an algorithm based on theoretical conditions.

result Proposes an algorithm to achieve lookahead counterfactual fairness and validates it on synthetic and real data.

counterfactual fairness downstream effects lookahead counterfactual fairness path-dependent fairness

2024-12-02abs ↗pdf ↗

Chronologically Consistent Large Language Modelsq-fin.GN

Chronologically consistent models maintain accuracy with time-restricted data.

problem Training data introduces lookahead bias and training leakage in large language models.

method ChronoBERT and ChronoGPT trained with only available data at each time point.

result Models achieve strong performance and competitive with larger models, mitigating lookahead bias.

chronological consistency lookahead bias training leakage large language models natural language processing

2025-02-28abs ↗pdf ↗

Improving the Predictive Performances of

k

Nearest Neighbors Learning by Efficient Variable Selectionstat.ML

Paper improves $k$ -NN predictive performance with efficient variable selection.

problem Improving predictive performance of

k

-NN models.

method Efficient forward selection of predictor variables.

result Novel approach approaches outperformance of stepwise selection models.

k-NN predictive performance variable selection forward selection stepwise selection

2022-11-04abs ↗pdf ↗

More Powerful and General Selective Inference for Stepwise Feature Selection using the Homotopy Continuation Approachstat.ML

Develops a more powerful selective inference method for stepwise feature selection.

problem Loss of power in existing conditional SI methods due to over-conditioning.

method Uses homotopy continuation approach to overcome over-conditioning.

result Shows improved power and efficiency in selective inference for feature selection.

Selective Inference Feature Selection Homotopy Continuation Stepwise Feature Selection Powerful Inference

2020-12-25abs ↗pdf ↗

Stepwise Model Selection for Sequence Prediction via Deep Kernel Learningcs.LG

Proposes a novel BO algorithm for stepwise model selection in sequence prediction.

problem Optimal model selection in sequential settings where model performance varies over time.

method Bayesian optimization with deep kernel learning to handle multiple black-box functions.

result Outperforms standard and multi-objective BO algorithms on sequence prediction tasks.

model selection sequence prediction Bayesian optimization deep kernel learning stepwise model selection

2020-01-12abs ↗pdf ↗

Autoregressive Language Models are Secretly Energy-Based Models: Insights into the Lookahead Capabilities of Next-Token Predictioncs.LG

This paper shows ARMs and EBMs are equivalent, revealing ARM lookahead capabilities.

problem Understanding the lookahead capabilities of next-token prediction models.

method Unified view of ARMs and EBMs, establishing a bijection and deriving equivalence.

result ARMs and EBMs are equivalent, revealing ARM lookahead capabilities.

autoregressive models energy-based models next-token prediction lookahead capabilities maximum entropy reinforcement learning

2025-12-17abs ↗pdf ↗

Two-step Lookahead Bayesian Optimization with Inequality Constraintsstat.ML

Efficiently optimizes constrained problems with two-step lookahead BO.

problem Optimizing constrained problems with limited computational resources.

method Two-step lookahead Bayesian optimization with inequality constraints, using a novel unbiased gradient estimator.

result Significantly improves query efficiency over previous methods.

Bayesian optimization constraint handling lookahead optimization unbiased gradient estimation

2021-12-06abs ↗pdf ↗

Adaptive Batching for Gaussian Process Surrogates with Application in Noisy Level Set Estimationstat.ML

Adaptive batching improves Gaussian process surrogates for noisy level set estimation.

problem Learning the level set of noisy simulator responses.

method Developed four novel adaptive batching schemes for Gaussian process metamodels.

result Adaptive batching brings significant computational speed-ups with minimal loss of modeling fidelity.

Gaussian process adaptive batching level set estimation replicated designs sequential design

2020-03-19abs ↗pdf ↗

Faster feature selection with a Dropping Forward-Backward algorithmstat.ML

A new algorithm speeds up feature selection by 65.77%.

problem Efficiently selecting features in high-dimensional data.

method Dropping Forward-Backward algorithm, reducing rescanning of features.

result Significantly faster than stepwise procedure, maintaining good performance.

feature selection forward-backward big data speed improvement high-dimensional

2019-10-17abs ↗pdf ↗

The Value of Reward Lookahead in Reinforcement Learningcs.LG

This work analyzes the value of future reward information in RL.

problem Analyzing the impact of knowing future rewards in reinforcement learning.

method Competitive analysis and worst-case reward distribution.

result Exact ratios between standard RL agents and those with future-reward lookahead.

reinforcement learning competitive analysis future rewards reward lookahead offline RL

2024-03-18abs ↗pdf ↗

Reinforcement Learning Architectures: SAC, TAC, and ESACcs.LG

ESAC improves reinforcement learning by lookahead and intuition.

problem Designing efficient reinforcement learning architectures for intelligent agents.

method Integrates selector, tuner, model-learner, estimator, and lookahead into ESAC.

result ESAC outperforms other architectures in optimizing policies.

reinforcement learning actor-critic lookahead intuition ESAC

2020-04-05abs ↗pdf ↗

Plancherel Formulae associated to Filtrations of Nilpotent Lie Groupsmath.RT

We study the conditions for a nilpotent Lie group to be foliated into subgroups that have square integrable (relative discrete series) unitary representations, that fit together to form a filtration by normal subgroups. Then we use that filtration to construct a class of "stepwise square integrable" representations on …

2012-12-09abs ↗pdf ↗

Improving Conditional Sequence Generative Adversarial Networks by Stepwise Evaluationcs.CL

Sequence generative adversarial networks (SeqGAN) have been used to improve conditional sequence generation tasks, for example, chit-chat dialogue generation. To stabilize the training of SeqGAN, Monte Carlo tree search (MCTS) or reward at every generation step (REGS) is used to evaluate the goodness of a generated sub…

2018-08-16abs ↗pdf ↗

Sequential design of multi-fidelity computer experiments: maximizing the rate of stepwise uncertainty reductionstat.AP

Maximal Rate of Stepwise Uncertainty Reduction selects simulations to reduce uncertainty efficiently.

problem Efficiently estimating quantities of interest from multi-fidelity simulations.

method Bayesian sequential strategy that maximizes the ratio of expected uncertainty reduction to simulation cost.

result MR-SUR strategy unifies and provides principled approaches to develop new methods.

Bayesian sequential design multi-fidelity uncertainty reduction fire safety

2020-07-27abs ↗pdf ↗

Bayesian Multiplicity Correction in the Probabilistic Forward Stepwise Frameworkmath.ST

Bayesian method corrects for model selection multiplicity in regression.

problem Model selection multiplicity in regression analysis.

method Developed a Bayesian prior distribution based on Holm procedure analogy.

result Adequate multiplicity correction requires sparsity not provided by recommended priors.

Bayesian statistics model selection multiplicity correction regression analysis Holm procedure

2026-05-27abs ↗pdf ↗

A Neural Spiking Approach Compared to Deep Feedforward Networks on Stepwise Pixel Erasementcs.LG

Spiking neural networks perform similarly to deep networks on occluded images.

problem Robust object recognition in partially occluded images.

method Developed a two-layer spiking neural network trained on natural scenes with a biologically plausible learning rule, compared to deep convolutional networks.

result Spiking neural networks achieve good accuracy and robustness on stepwise pixel erasement tasks.

spiking neural networks deep learning object recognition occlusion MNIST

2019-12-06abs ↗pdf ↗

Nonmyopic Global Optimisation via Approximate Dynamic Programmingcs.LG

New methods improve global optimisation for expensive functions using lookahead strategies.

problem Optimising expensive functions without gradient info in high dimensions.

method Nonmyopic acquisition strategies based on approximate dynamic programming.

result Nonmyopic methods outperform myopic approaches in various applications.

global optimisation approximate dynamic programming nonmyopic acquisition expensive functions sequential decision making

2024-12-06abs ↗pdf ↗

Improved identification accuracy in equation learning via comprehensive

\boldsymbol{R^2}

-elimination and Bayesian model selectionstat.ML

Improved equation learning accuracy via comprehensive R²-elimination and Bayesian model selection.

problem Challenges in exhaustive equation learning due to multicollinearity and greedy steps.

method Combines

R^2

and Bayesian model evidence for a comprehensive yet efficient search.

result Our approach surpasses all other methods in identification accuracy, especially in exact equation recovery.

equation learning multicollinearity stepwise regression Bayesian model selection comprehensive search

2023-11-22abs ↗pdf ↗

Penalizing side effects using stepwise relative reachabilitycs.LG

How can we design safe reinforcement learning agents that avoid unnecessary disruptions to their environment? We show that current approaches to penalizing side effects can introduce bad incentives, e.g. to prevent any irreversible changes in the environment, including the actions of other agents. To isolate the source…

2018-06-04abs ↗pdf ↗

A New Forward Discriminant Analysis Framework Based On Pillai's Trace and ULDAstat.ME

New framework improves classification accuracy using Pillai's trace and ULDA.

problem Traditional LDA's limitations in noise sensitivity and non-invertible matrices.

method Integrates Pillai's trace with ULDA for a unified classifier.

result Effective control of Type I error rates and improved classification accuracy.

discriminant analysis Pillai's trace ULDA classification accuracy Type I error

2024-09-05abs ↗pdf ↗