arXiv research

A new strategy selects k in k-NN regression without hold-out data.

Paper proposes a method for early stopping in regression using reproducing kernels.

When maximum likelihood estimation is infeasible, one often turns to score matching, contrastive divergence, or minimum probability flow to obtain tractable parameter estimates. We provide a unifying perspective of these techniques as minimum Stein discrepancy estimators, and use this lens to design new diffusion kerne…

Study on discrepancy principle for learning algorithms in nonparametric regression.

Study shows the corrected Akaike criterion is inadmissible for estimating Kullback-Leibler discrepancy.

New partition designs reduce star discrepancy in high-dimensional sampling.

Human decision-making deviates from the optimal solution, that maximizes cumulative rewards, in many situations. Here we approach this discrepancy from the perspective of bounded rationality and our goal is to provide a justification for such seemingly sub-optimal strategies. More specifically we investigate the hypoth…

Improved MMD estimator for likelihood-free inference.

Study of complex Hessian equations using subharmonic functions and geodesics.

New principle controls graph-informed adversarial discrepancies.

New method for adaptive estimation and inference in econometric models without knowing smoothness.

Suppose $f(x,y) + \fracκ{2} \|x\|^2 - \fracσ{2}\|y\|^2$ is convex where $σ>0$, and the argmin function $γ(x) = \{ γ: \inf_y f(x,y) = f(x,γ)\}$ exists and is single valued. We will prove $γ$ is differentiable almost everywhere. As an application we deduce a minimum principle for certain semiconcave subsolutions.

First principles modeling of physical systems has led to significant technological advances across all branches of science. For nonlinear systems, however, small modeling errors can lead to significant deviations from the true, measured behavior. Even in mechanical systems, where the equations are assumed to be well-kn…

Exponential models of distributions are widely used in machine learning for classiffication and modelling. It is well known that they can be interpreted as maximum entropy models under empirical expectation constraints. In this work, we argue that for classiffication tasks, mutual information is a more suitable informa…

This paper provides a geometrical derivation of the Hybrid Minimum Principle (HMP) for autonomous hybrid systems whose state manifolds constitute Lie groups $(G,\star)$ which are left invariant under the controlled dynamics of the system, and whose switching manifolds are defined as smooth embedded time invariant subma…

We analyze differences between two information-theoretically motivated approaches to statistical inference and model selection: the Minimum Description Length (MDL) principle, and the Minimum Message Length (MML) principle. Based on this analysis, we present two revised versions of MML: a pointwise estimator which give…

The Ekeland variational principle implies what can be regarded as a strong version, in the $C^1$ category, of the Yau minimum principle: under the appropriate hypotheses {\it every} minimizing sequence admits a {\it good shadow}, a second minimizing sequence that has good properties and is asymptotic to the original on…

In this paper we are dealing with two classes of mean curvature type problems that generalize the translating soliton problem. A first result proves that the solutions to these problems have unique interior critical points. Using this uniqueness result, we next derive a priori $C^0$ and $C^1$ estimates for the solution…

MMD test detects adversarial attacks by addressing kernel limitations and non-independence issues.

Framework identifies discrepancies in physics models, improving sensor accuracy.

We study strictly proper scoring rules in the Reproducing Kernel Hilbert Space. We propose a general Kernel Scoring rule and associated Kernel Divergence. We consider conditions under which the Kernel Score is strictly proper. We then demonstrate that the Kernel Score includes the Maximum Mean Discrepancy as a special …

Imitation learning trains a policy from expert demonstrations. Imitation learning approaches have been designed from various principles, such as behavioral cloning via supervised learning, apprenticeship learning via inverse reinforcement learning, and GAIL via generative adversarial learning. In this paper, we propose…

The economic life of an asset is the optimum length of its usefulness, which is the moment that the asset's expenses are minimum. In this paper, the economic life of physical assets, such as industry machine and equipment, can be interpreted as the moment that the minimum is reached by its equivalent property cost func…

A new loss function ED simplifies training energy-based models without scores.

This work proposes a new method to match distributions across different spaces using cycle-consistent maps.

PCA (Principal Component Analysis) and its variants areubiquitous techniques for matrix dimension reduction and reduced-dimensionlatent-factor extraction. One significant challenge in using PCA, is thechoice of the number of principal components. The information-theoreticMDL (Minimum Description Length) principle gives…

Paper proposes deep neural networks for nonparametric regression from dependent data.

Minimum attention improves reinforcement learning performance in high-dimensional dynamics.

Paper proposes kernel-based tests for model misspecification.

Plug-in robust NPE method adapts summaries independently of pretrained NPE.

Paper explores Fisher-Rao gradient flows and their kernel approximations.

Optimizes control of infectious disease spread using stochastic methods.

We tackle the problem of penalty selection of regularization on the basis of the minimum description length (MDL) principle. In particular, we consider that the design space of the penalty function is high-dimensional. In this situation, the luckiness-normalized-maximum-likelihood(LNML)-minimization approach is favorab…

Time-invariant linear dynamical system arises in many real-world applications,and its usefulness is widely acknowledged. A practical limitation with this model is that its latent dimension that has a large impact on the model capability needs to be manually specified. It can be demonstrated that a lower-order model cla…

New method improves MMD estimation without convexity assumptions.

Study on maximum principles for nonlinear equations on Riemannian manifolds.

Study shows LLC correlates with neural network compressibility.

New technique clusters and classifies datasets with missing attributes.

We propose a notion of distance between two parametrized planar curves, called their discrepancy, and defined intuitively as the minimal amount of deformation needed to deform the source curve into the target curve. A precise definition of discrepancy is given as follows. A curve of transformations in the special Eucli…

New algorithm tunes SGMCMC hyperparameters for scalable Bayesian inference.

A new method avoids overfitting in network reconstruction by using the minimum description length principle.

New knots found with Seifert genus not matching minimal genus Seifert surfaces.

SENA-discrepancy-VAE interprets latent causal factors in biological pathways.

New measure shows how links can be untangled as twists increase.

New proof given for a functional's minimum condition.

Framework identifies causal direction from single data setting.

This article is written for the Proceedings of the Conference on Current Developments in Mathematics in Harvard University, November 16-17, 2007. It is an exposition of the analytic proof of the finite generation of the canonical ring for a compact complex algebraic manifold of general type. It lists and discusses the …

In this paper, we use the distance comparison principle, first been developed by G. Huisken, to study the spatial curve shortening flow. We have got the result that if the initial curve is the helix, then the local minimum of the ratio of the extrinsic and intrinsic distance is non-decreasing. And we have proved a Gray…