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.

169,181 papers · 148 categories

Trend · papers per month

4079119158 · May 202619922001200920182026
48 results for moment alignment

Unified approach to domain generalization by aligning gradients and Hessians.

problem Developing models that generalize well across unseen domains.
method Moment Alignment, extending transfer measure to DG, aligning derivatives across domains.
result Moment Alignment unifies gradient and Hessian matching approaches, improving generalizability.

Unified framework for distribution shift estimation, explanation, and improvement.

problem Estimating, explaining, and improving model performance on target domains with distribution shift.
method Entropic Projection Alignment (EPA) aligns source and target distributions by matching moments and minimizing KL divergence.
result EPA consistently outperforms state-of-the-art baselines while offering computational efficiency.

Proposes DWMD for better matching of hidden representations across domains.

problem Measuring data distribution discrepancy between semantically related domains for feature representation matching.
method DWMD, a moment-based probability distribution metric that explicitly orders and weights higher-order moments.
result DWMD is error-free and can strictly reflect distribution differences without feature distribution assumptions.

A new method for neural networks adapts to different domains without labeled data.

problem Adapting neural networks to new domains without labeled data.
method Metric-based regularization to maximize similarity of domain-specific activation distributions by aligning moments.
result The method achieves higher classification accuracies than existing approaches.

Weibull weight-scale parameter λλ evolves during AdamW training, with alignment, injection, and decay forces driving its growth and relaxation.

problem Understanding the evolution of the Weibull weight-scale parameter λλ during AdamW training.
method Deriving a leading-order three-force decomposition of the squared weight norm from AdamW updates.
result The alignment force dominates the rise phase, contributing 88-94% of the absolute force budget across four random seeds.

Learning rate needs to decrease with higher data moments for effective ICA in high dimensions.

problem Slower convergence of ICA in high-dimensional data with high-order moments.
method High-dimensional ODE analysis of ICA algorithm under controlled moment structure.
result Critical learning rate threshold for effective ICA when moments are high.

We present a novel framework for kernel learning with sequential data of any kind, such as time series, sequences of graphs, or strings. Our approach is based on signature features which can be seen as an ordered variant of sample (cross-)moments; it allows to obtain a "sequentialized" version of any static kernel. The…

2016-01-29abs ↗pdf ↗

Mixture models are a fundamental tool in applied statistics and machine learning for treating data taken from multiple subpopulations. The current practice for estimating the parameters of such models relies on local search heuristics (e.g., the EM algorithm) which are prone to failure, and existing consistent methods …

2012-03-03abs ↗pdf ↗

The moments of historic stock returns align with the Heston model, not the multiplicative model.

problem Understanding the distribution of historic stock returns and volatility.
method Comparison of moments with Heston and multiplicative models, analysis of mean realized variance.
result The moments of historic stock returns are better explained by the Heston model than the multiplicative model.

Estimates KRR risk from training data for various kernels and hyperparameters.

problem Predicting the generalization error of Kernel Ridge Regression.
method Introduces SCT and KARE to approximate KRR risk from training data.
result KARE provides an excellent approximation of KRR risk and helps select good kernels.

EnMDAP aligns conditional distributions for multi-source domain adaptation using pseudolabels.

problem Training a target model with no labeled data in the absence of target data labels.
method EnMDAP uses label-wise moment matching and ensemble learning with multiple feature extractors.
result EnMDAP achieves state-of-the-art performance in multi-source domain adaptation tasks.

Study confirms optimal minimax rate for nonlocal interaction kernel estimation.

problem Estimating nonlocal interaction kernels in interacting particle systems.
method Introduced tamed least squares estimator (tLSE) achieving optimal convergence rate.
result Optimal minimax rate of convergence confirmed for β1/4β \geq 1/4.

Optimal transport theory characterizes convex order between probability measures.

problem Characterizing convex order between probability measures using optimal transport.
method Quantitative bounds on optimal transport, infimum of functionals over 1-Lipschitz functions.
result Two measures are in convex order if and only if a specific cost functional inequality holds.

Paper introduces REED for noncoherent OTA-FL, reducing latency without phase alignment.

problem Noncoherent OTA-FL requires signed model updates without phase alignment.
method Introduces REED for continuous signed aggregation using resource-element energy difference.
result Exact variance laws for REED and chip-diverse extension in Rayleigh fading.

Paper analyzes LSA algorithm bias and error bounds with RR extrapolation.

problem Analyzing bias and high-order error bounds of LSA with Markovian noise.
method Polyak-Ruppert averaging, linearization, Richardson-Romberg extrapolation.
result RR extrapolation effectively cancels the leading bias term.

The paper addresses score-mismatched diffusion models and zero-shot conditional samplers.

problem Theoretical guarantees for score-mismatched diffusion models in zero-shot conditional sampling.
method Theoretical analysis of score-mismatched diffusion models and zero-shot conditional samplers.
result Theoretical performance guarantees with explicit dimensional dependencies for score-mismatched diffusion samplers.

The paper applies Fisher-Rao geometry to beta distributions for moment analysis.

problem Comparing and analyzing moments of probability distributions.
method Derived geodesic equations and sectional curvature on beta distributions' parameter space. Used Fisher-Rao geometry to map canonical moments to beta distributions.
result Uniqueness of Riemannian centroid in beta distributions' parameter space.

Inference-aware meta-alignment of LLMs reduces computational cost.

problem Aligning LLMs to diverse human preferences is challenging due to conflicting criteria.
method IAMA trains a base model to be aligned to multiple tasks via different inference-time alignment algorithms, using non-linear GRPO for optimization.
result IAMA enables effective alignment of LLMs to multiple criteria with limited computational budget.

This paper identifies and bounds ICE central moments using PO marginal central moments.

problem Identifying and characterizing treatment effect heterogeneity.
method Using only marginal central moments of potential outcomes, the paper identifies and bounds central moments of individual causal effects.
result Identification and bounding of central moments of ICE using marginal moments of POs.

We tackle causal inference under conditional moment restrictions using importance weighting.

problem Challenges in causal inference under conditional moment restrictions, especially in high-dimensional settings.
method Transform conditional moment restrictions to unconditional moment restrictions through importance weighting.
result Successfully estimate nonparametric functions defined under conditional moment restrictions.

Conformal Alignment ensures trustworthy outputs from foundation models.

problem Ensuring outputs from foundation models align with human values in high-stakes tasks.
method A framework that trains an alignment predictor using reference data to select trustworthy outputs.
result Conformal Alignment accurately identifies trustworthy outputs via lightweight training over moderate reference data.

A new method for estimating causal parameters from observables reduces the need for finite moment conditions.

problem Estimating causal parameters from observational data with unknown or infinite moment conditions.
method Variational Method of Moments (VMM) for a general class of estimators, including kernel and neural net-based methods.
result VMM estimators are consistent, asymptotically normal, and semiparametrically efficient.

Introduces generalized moment maps for almost Hermitian settings.

problem Extending classical moment map theory to almost Hermitian settings.
method Introduces momentumly closed forms and proves a variant of the Darboux-Weinstein theorem.
result Establishes convexity property and constructs reduction space for generalized moment maps.

Proposes Moment Exchange to use moments in image recognition models, improving generalization.

problem Discarding moments in image recognition models reduces stability and training time.
method Moment Exchange: replaces moments of learned features with another image's moments and interpolates labels.
result Improves generalization of recognition models across multiple datasets.

LPL optimizes embeddings to align local neighborhoods, improving cross-lingual word alignment.

problem Aligning embeddings across different datasets and languages.
method Locality Preserving Loss (LPL) optimizes model to project embeddings while maintaining local neighborhoods and aligning them.
result LPL-based alignment leads to better and consistent accuracy, especially in small training set settings.

Method learns moments for large implicit models, improving image generation quality.

problem Difficulty in defining and selecting moments for training large implicit models.
method Introduced moment network and used asymptotic theory to define and learn better moments.
result MoLM-trained generators outperform other methods in quality and diversity of generated images.

Extends reinforcement learning alignment to scalar rewards, improving math reasoning.

problem Designing reinforcement learning algorithms for general LLM alignment.
method Introduces f-GRPO and f-HAL, estimating f-divergences between reward-aligned and unaligned distributions.
result Improves math reasoning RLVR tasks and mitigates reward hacking.

A new method of moments estimator goes beyond data reweighting.

problem Estimation of moment restrictions and conditional moment restrictions.
method Kernel Method of Moments (KMM) based on maximum mean discrepancy.
result KMM achieves competitive performance on conditional moment restriction tasks.

Moment Pooling reduces latent space dimensions in machine learning models.

problem High-dimensional latent spaces in machine learning models are hard to interpret.
method Moment Pooling extends Deep Sets networks to arbitrary multivariate moments.
result Latent dimensions as small as 1 can achieve similar performance to higher dimensions.

Paper proposes unsupervised knowledge graph alignment with adversarial learning.

problem Aligning knowledge graphs from different sources or languages without large amounts of aligned triplets.
method Adversarial learning framework to align entity and relation embeddings, with mutual information regularization.
result Framework effectively aligns knowledge graphs in unsupervised and weakly-supervised settings.