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.

168,742 papers · 148 categories

Trend · papers per month

70139209278 · Jun 202019922001200920172026
48 results for corrective step

Improved solver maintains positivity and accuracy across all time steps.

problem Linear second-order schemes for Fokker-Planck equation cannot preserve positivity.
method Flux-Corrected Diagonal Frog (FCDF) framework using nonlinear extension and iterative limiter.
result FCDF schemes are unconditionally positive across all time steps and maintain second-order accuracy.

AMAGOLD improves stochastic gradient MCMC by infrequent Metropolis-Hastings corrections.

problem Bias in stochastic gradient Hamiltonian Monte Carlo (SGHMC).
method AMAGOLD infrequently uses Metropolis-Hastings corrections to remove bias, with a fixed step size schedule.
result AMAGOLD converges to the target distribution with a fixed, rather than a diminishing, step size, and at most a constant factor slower convergence rate.

Theoretical work shows integrating coherent reasoning improves LLM performance and error correction.

problem Improving reasoning and error correction in large language models (LLMs) with few-shot prompting.
method Theoretical analysis and sensitivity experiments on transformer behavior with coherent reasoning and corrupted demonstrations.
result The transformer gains better error correction ability and more accurate predictions when coherent reasoning is integrated.

One-step Bellman alignment improves online RL by reducing task mismatch.

problem Online RL struggles with task similarity defined by rewards or transitions.
method One-step Bellman alignment and re-weighted targeting (RWT) to correct task mismatch.
result Regret bounds show task shift complexity, not target MDP, affects performance.

We present a predictor-corrector framework, called PicCoLO, that can transform a first-order model-free reinforcement or imitation learning algorithm into a new hybrid method that leverages predictive models to accelerate policy learning. The new "PicCoLOed" algorithm optimizes a policy by recursively repeating two ste…

2018-10-15abs ↗pdf ↗

The paper corrects for node degree in spectral clustering using random walk Laplacian.

problem Node degree heterogeneity in spectral clustering.
method Graph spectral embedding using the random walk Laplacian.
result The embedding provides uniformly consistent estimates of degree-corrected latent positions.

GrowNet uses shallow neural networks for gradient boosting, outperforming existing methods.

problem Improving gradient boosting performance through shallow neural networks.
method Unified gradient boosting framework with shallow neural networks as weak learners, incorporating corrective steps.
result GrowNet outperformed state-of-the-art boosting methods in classification, regression, and learning to rank tasks.

Proposes SD-KDE for density estimation using debiased kernel density with score-based adjustments.

problem Density estimation with bias in kernel density estimation.
method Adjusts data points by taking a step along the estimated score function, then applies standard KDE with modified bandwidth.
result Significantly reduces mean integrated squared error compared to standard Silverman KDE, especially with noisy score function estimates.

A new method uses denoising diffusion models to improve seismic data interpolation.

problem Improving the accuracy of seismic data interpolation to enhance imaging and interpretation.
method The approach combines denoising diffusion probabilistic models with coherence-corrected resampling strategies.
result The proposed method achieves superior performance and generalization to various missing patterns and noise levels.

We propose and analyze an alternate approach to off-policy multi-step temporal difference learning, in which off-policy returns are corrected with the current Q-function in terms of rewards, rather than with the target policy in terms of transition probabilities. We prove that such approximate corrections are sufficien…

2016-02-16abs ↗pdf ↗

Theoretical analysis shows LLMs can self-correct responses through in-context learning.

problem Understanding how large language models improve through self-correction.
method Theoretical analysis based on simplified alignment task, focusing on softmax attention, multi-head attention, and MLP blocks.
result LLMs can refine responses in an in-context way when given accurate self-examinations as rewards.

Neural CDEs correct errors in learned time-series models for better forecasting.

problem Error accumulation in multi-step forecasts of learned time-series models.
method Predictor-Corrector framework with a neural controlled differential equation.
result The proposed framework consistently improves forecasting performance across various models.

The paper corrects biases in estimating intrinsic dimension and differential entropy.

problem Systematic bias in estimating intrinsic dimension and differential entropy.
method A bias-corrected estimator for both measures is proposed, highlighting shared steps and useful consequences.
result Simultaneous estimation of differential entropy and intrinsic dimension provides complementary perspectives on underlying manifolds.

We construct an extension of the Kontsevich integral of knots to knotted trivalent graphs, which commutes with orientation switches, edge deletions, edge unzips, and connected sums. In 1997 Murakami and Ohtsuki [MO] first constructed such an extension, building on Drinfel'd's theory of associators. We construct a step …

2008-11-27abs ↗pdf ↗

A new subdivision scheme for Heisenberg group values with central smoothness loss.

problem Regularity of limit curves in Heisenberg group-valued subdivision schemes.
method Interpolatory subdivision scheme with central correction based on group law.
result Central part of limit curve converges to a continuous limit with logarithmic modulus of continuity.

A method corrects bias in estimating a high-dimensional classification rule using auxiliary outcomes.

problem Bias in estimating a high-dimensional classification rule using only one outcome.
method Robust transfer learning approach combining MTL and calibration steps.
result Final estimator achieves lower error than using only the target outcome.

Paper analyzes convergence of PAM method for low-rank factorization models.

problem Convergence analysis of PAM method with subspace correction for low-rank factorization models.
method Majorized proximal alternating minimization (PAM) method with subspace correction.
result Established full convergence of PAM method under KL property and column 2,0\ell_{2,0}-norm condition.

Closed formulas for η-corrections in the once-punctured torus identified.

problem Identifying η-corrections in the Kauffman bracket skein algebra of the once-punctured torus.
method Explicit closed formulas for Chebyshev-threaded families and η-corrections.
result Explicit Chebyshev expansions and coefficients for η-corrections.

Improved robustness for high-dimensional Kalman filtering.

problem Convergence issues in sequential variational inference filter (VIF).
method Variational Kalman Filtering with Hinf-based correction.
result Improved feasibility and robustness in high-dimensional systems.

Improved Markov models learn from their mistakes and adapt to problem complexity.

problem Limitations of standard masked discrete diffusion models in reasoning tasks.
method Learning a Markov transition kernel trained on its own outputs, allowing remasking and adaptation.
result Significant improvement in solving reasoning problems, especially Sudoku-Extreme and Countdown-4.

Method guarantees coherent factuality for language model outputs in reasoning tasks.

problem Ensuring correctness of language model outputs in reasoning tasks.
method Developed a conformal-prediction-based method applied to subgraphs within a deducibility graph.
result Achieved coherent factuality across target coverage levels, 90% on stricter definition.

Corrects local error estimates for UBU integrator in SDEs, improving complexity guarantees.

problem Improper local error estimates in UBU integrator for SDEs.
method Reconciles theory with practice by correcting local error estimates.
result Stronger assumptions needed for O(d1/4ε1/2)\mathcal{O}(d^{1/4}ε^{-1/2}) steps in Wasserstein-2 distance.

Human communication takes many forms, including speech, text and instructional videos. It typically has an underlying structure, with a starting point, ending, and certain objective steps between them. In this paper, we consider instructional videos where there are tens of millions of them on the Internet. We propose a…

2016-05-11abs ↗pdf ↗

Multi-hop inference is necessary for machine learning systems to successfully solve tasks such as Recognising Textual Entailment and Machine Reading. In this work, we demonstrate the effectiveness of adaptive computation for learning the number of inference steps required for examples of different complexity and that l…

2016-10-24abs ↗pdf ↗

Theoretical analysis shows MDMs can be efficient but not for all metrics.

problem Understanding the efficiency-accuracy trade-off of diffusion language models.
method Theoretical analysis of Masked Diffusion Model (MDM) using perplexity and sequence error rate as metrics.
result MDM achieves near-optimal perplexity but requires linear scaling for sequence error rate, highlighting efficiency-accuracy trade-offs.

New estimator improves off-policy evaluation for large action spaces.

problem Conventional importance-weighting approaches suffer from excessive variance in off-policy evaluation for large discrete action spaces.
method Proposes OffCEM estimator based on conjunct effect model (CEM), applying importance weighting only to action clusters and using model-based reward estimation for residual effects.
result Proposed estimator is unbiased under local correctness condition, providing substantial improvements in OPE especially with many actions.

Reasoning models generate differently based on problem difficulty, not just length.

problem Understanding how reasoning models handle different problem difficulties.
method Examined hidden-state trajectories across competitive programming, mathematics, and Boolean satisfiability.
result Corrected trajectory geometry shows difficulty-dependent differences in reasoning models, with stronger effects in the code domain.

Corrected samplers reduce discretization error in discrete flow models without additional computational cost.

problem Discretization error in samplers for discrete flow models.
method Established non-asymptotic error bounds for samplers, proposed time-corrected and location-corrected samplers.
result Location-corrected sampler has lower complexity and better generation quality.

Proposes a method to estimate conditional quantiles using both high-fidelity and low-fidelity data.

problem Difficulty in estimating conditional quantiles with scarce high-fidelity data.
method Two-stage, model-agnostic method using local quantile link and level function estimation.
result The method yields more accurate quantile estimates and tighter prediction intervals.

The recent use of `Big Code' with state-of-the-art deep learning methods offers promising avenues to ease program source code writing and correction. As a first step towards automatic code repair, we implemented a graph neural network model that predicts token types for Javascript programs. The predictions achieve an a…

2019-05-16abs ↗pdf ↗