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.

168,657 papers · 148 categories

Trend · papers per month

4080120160 · Jun 202019922001200920172026
48 results for Current-theoretic formulation

Formula for sections on complex manifolds with non-isolated components.

problem Localization of sections on complex manifolds with non-isolated zero varieties.
method Logarithmic Bott localization formula, current-theoretic formulation.
result Established a formula for sections on compact complex manifolds with non-isolated components.

A very simple interpretation of matrix completion problem is introduced based on statistical models. Combined with the well-known results from missing data analysis, such interpretation indicates that matrix completion is still a valid and principled estimation procedure even without the missing completely at random (M…

2016-05-10abs ↗pdf ↗

Unified physics-informed learning method improves generalization performance.

problem Lack of theoretical analysis for hybrid settings with incomplete physical constraints.
method Unified residual form unifying collocation and variational methods, establishing generalization performance governed by affine variety dimension.
result Generalization performance is determined by affine variety dimension, not just the number of parameters.

This work analyzes discrete diffusion models using stochastic integrals, providing error bounds and insights.

problem Error analysis for discrete diffusion models remains less understood.
method Proposes a comprehensive framework based on Lévy-type stochastic integrals.
result Obtains the first error bound for the ττ-leaping scheme in KL divergence.

Domain adaptation (DA) is an important and emerging field of machine learning that tackles the problem occurring when the distributions of training (source domain) and test (target domain) data are similar but different. Current theoretical results show that the efficiency of DA algorithms depends on their capacity of …

2016-10-14abs ↗pdf ↗

The paper explores grokking in various models, revealing it's not limited to neural networks.

problem Understanding grokking in different models and its mechanism.
method Empirical exploration of grokking in neural networks, Gaussian processes, linear regression, and Bayesian neural networks. Inducing grokking through spurious dimensions.
result Grokking occurs in non-neural architectures, indicating it's not model-specific.

Matrix completion is a well-studied problem with many machine learning applications. In practice, the problem is often solved by non-convex optimization algorithms. However, the current theoretical analysis for non-convex algorithms relies heavily on the assumption that every entry is observed with exactly the same pro…

2018-03-28abs ↗pdf ↗

New findings show neural network training loss follows a power law over time.

problem Understanding the optimization process of neural networks during training.
method Spectral analysis of the integral operator representing the linearized evolution of a large network.
result The loss function in neural network training follows a power law behavior, L(t)tξL(t) \sim t^{-ξ}, with exponent ξξ determined by network parameters and data characteristics.

CoT improves transformer sample efficiency by reducing input token dependencies and attention sparsity.

problem Transformer sample inefficiency in simple tasks.
method Demonstrated through parity-learning setup, showing CoT reduces required samples from exponential to polynomial.
result Transformer learns function within polynomial samples with CoT, requiring exponential samples without CoT.

We consider the problem of recovering a low-rank matrix from its clipped observations. Clipping is conceivable in many scientific areas that obstructs statistical analyses. On the other hand, matrix completion (MC) methods can recover a low-rank matrix from various information deficits by using the principle of low-ran…

2018-09-13abs ↗pdf ↗

We analyze double descent in finite-width neural networks using influence functions.

problem Understanding double descent in finite-width neural networks.
method Using influence functions to derive population loss bounds and investigate loss function effects.
result Derived bounds exhibit double descent behavior at the interpolation threshold.

The paper addresses adversarial robustness in in-context learning models.

problem Adversarial distribution shifts threaten the reliability of in-context learning models.
method A distributionally robust meta-learning framework is introduced to provide worst-case performance guarantees under Wasserstein-based distribution shifts.
result Model robustness scales with the square root of its capacity and is penalized by the square of the perturbation magnitude.

Unsupervised learning is widely recognized as one of the most important challenges facing machine learning nowa- days. However, in spite of hundreds of papers on the topic being published every year, current theoretical understanding and practical implementations of such tasks, in particular of clustering, is very rudi…

2018-05-22abs ↗pdf ↗

This work analyzes tree-based methods from a ranking perspective, providing insights and new statistics.

problem Understanding the effectiveness of tree-based methods in finite-sample settings, especially symbolic feature selection.
method Local ranking perspective, finite-sample analysis, oracle bounds, posterior contraction results, concordant divergence statistics.
result New insights and statistics for evaluating symbolic feature mappings.

Unified analysis of self-training for deep networks on unlabeled data.

problem Theoretical understanding of self-training for deep networks on unlabeled data.
method Unified theoretical analysis using expansion assumption and input-consistency regularization.
result Proves high accuracy of minimizers of population objectives based on self-training and input-consistency regularization.

New algorithm reduces policy regret in tallying bandits.

problem Measuring online learning performance against adaptive adversaries.
method Tallying bandit model, efficient algorithm with complete policy regret guarantee.
result Achieves a complete policy regret guarantee of ildeO(mKT) ilde{\mathcal{O}}(mK\sqrt{T}).

ReLU neural-networks have been in the focus of many recent theoretical works, trying to explain their empirical success. Nonetheless, there is still a gap between current theoretical results and empirical observations, even in the case of shallow (one hidden-layer) networks. For example, in the task of memorizing a ran…

2019-06-12abs ↗pdf ↗

Gradient Boosting Machine (GBM) introduced by Friedman is a powerful supervised learning algorithm that is very widely used in practice---it routinely features as a leading algorithm in machine learning competitions such as Kaggle and the KDDCup. In spite of the usefulness of GBM in practice, our current theoretical un…

2018-10-24abs ↗pdf ↗

The paper analyzes learning curves for kernel ridge regression with dot-product kernels.

problem Understanding the learning curves for different scaling regimes of data and model.
method Precise formulas for mean test error, bias, and variance in the mom o\infty with m/drm/d^r constant regime.
result A peak in the learning curve at mdr/r!m \approx d^r/r! for any integer rr.

A new method reduces complexity of normalizing flows for MCMC preconditioning.

problem Improving sampling efficiency in MCMC algorithms for complex target distributions.
method Factorized preconditioning architecture combining a linear component and a conditional NF.
result Significantly better tail samples and higher effective sample sizes on various distributions.

Gluon optimizes LMO-based methods for large-scale tasks, improving performance and theory-practice gap.

problem LMO-based methods lack theoretical support for practical implementation and smoothness assumptions.
method Introduces Gluon, a new LMO-based method with refined smoothness model.
result Gluon's theoretical stepsizes match fine-tuned values, closing the theory-practice gap.

New method uses sparse deep neural networks for high-dimensional regression with improved parameter estimation.

problem Improving parameter estimation in high-dimensional sparse regression models.
method Proposes nonparametric estimation of partial derivatives in sparse deep neural networks.
result Established convergence rate of nonparametric estimation of partial derivatives as O(n1/4)\mathcal{O}(n^{-1/4}).

New method accelerates diffusion models for broader target distributions.

problem Current diffusion models have limited acceleration for certain target distributions.
method Developed a novel accelerated stochastic DDPM sampler.
result Achieved accelerated performance for three broad distribution classes.

Over-parameterized models reduce Out-of-Distribution (OOD) generalization loss.

problem Understanding how over-parameterized models handle non-trivial distributional shifts.
method Investigating random feature models and examining non-trivial natural distributional shifts.
result Increasing model parameterization reduces OOD loss.

Survey on random features for kernel approximation, focusing on algorithms, theory, and practical applications.

problem Efficiently approximating kernel methods for large-scale problems.
method Random features techniques to speed up kernel methods.
result Need for a high number of random features for good approximation quality.

Optimal data-driven formulations are found for learning and decision-making with historical data.

problem Designing optimal learning and decision-making formulations from historical data.
method Define a yardstick for measuring formulation quality, then construct an optimal formulation that is uniformly closer to the true cost.
result Existence of three distinct out-of-sample performance regimes with corresponding optimal formulations.

Paper proposes a QUBO formulation that reduces binary variables in Bayesian network learning.

problem Reducing the number of binary variables in QUBO formulations for Bayesian network learning.
method Proposes a new QUBO formulation that minimizes binary variables.
result Significantly reduces the number of binary variables required for Bayesian network structure learning.

Defines a metric and form for a bundle moduli space, leading to a zero-curvature formulation.

problem Formulating a metric and form for a bundle moduli space.
method Defines an algebraic metric and closed 3-form on a subspace of the moduli of GG-bundles.
result Shows a zero-curvature formulation for a σσ-model with target the moduli space.

We study ranking quantilized mean-field games to select top-performing agents.

problem Selecting top-performing agents in competitive scenarios.
method Developed two formulations: target-based and threshold-based, and provided analytic and semi-explicit solutions.
result Analytic and semi-explicit solutions for quantilized mean-field consistency conditions.

New conic quadratic formulations improve outlier detection in regression models.

problem Detecting outliers in regression models with corrupted data.
method Deriving stronger second-order conic relaxations without big-M constraints.
result Proposed formulations are significantly faster than existing methods.

The paper develops mixed-integer formulations for neural networks using partitioning.

problem Optimizing trained ReLU neural networks with balanced model size and tightness.
method Partitioning node inputs into groups, forming the convex hull via disjunctive programming.
result The proposed formulations outperform existing ones, especially with fewer partitions.

Equivalent formulations for low-rank matrix optimization are proven.

problem Low-rank matrix optimization with rank constraints.
method Established geometric landscape connections between manifold and factorization formulations.
result Equivalence between manifold and factorization formulations at FOSPs, SOSPs, and strict saddles.

A new Lagrangian formulation of the Raychaudhuri equation in non-Riemannian geometry.

problem Formulating the Raychaudhuri equation in non-Riemannian geometries.
method Established a formal connection between the expansion scalar and the cross-sectional volume of the congruence. Derived a Lagrangian and Hamiltonian formulation.
result The expansion scalar equals the fractional rate of change of volume, weighted by a scalar factor.

We propose a parallelizable sparse inverse formulation Gaussian process (SpInGP) for temporal models. It uses a sparse precision GP formulation and sparse matrix routines to speed up the computations. Due to the state-space formulation used in the algorithm, the time complexity of the basic SpInGP is linear, and becaus…

2016-10-25abs ↗pdf ↗

Dirac structures are geometric objects that generalize both Poisson structures and presymplectic structures on manifolds. They naturally appear in the formulation of constrained mechanical systems. In this paper, we show that the evolution equa- tions for nonequilibrium thermodynamics admit an intrinsic formulation in …

2017-04-12abs ↗pdf ↗

The optimal binning is the optimal discretization of a variable into bins given a discrete or continuous numeric target. We present a rigorous and extensible mathematical programming formulation for solving the optimal binning problem for a binary, continuous and multi-class target type, incorporating constraints not p…

2020-01-22abs ↗pdf ↗