arXiv research

This paper improves model generalization by integrating diverse pretrained models.

In this paper, we design and analyze a new zeroth-order online algorithm, namely, the zeroth-order online alternating direction method of multipliers (ZOO-ADMM), which enjoys dual advantages of being gradient-free operation and employing the ADMM to accommodate complex structured regularizers. Compared to the first-ord…

We study del Pezzo surfaces that are quasismooth and well-formed weighted hypersurfaces. In particular, we find all such surfaces whose alpha-invariant of Tian is greater than 2/3.

In the eyes of a rationalist like Descartes or Spinoza, human reasoning is flawless, marching toward uncovering ultimate truth. A few centuries later, however, culminating in the work of Kahneman and Tversky, human reasoning was portrayed as anything but flawless, filled with numerous misjudgments, biases, and cognitiv…

Measuring the morphological parameters of galaxies is a key requirement for studying their formation and evolution. Surveys such as the Sloan Digital Sky Survey (SDSS) have resulted in the availability of very large collections of images, which have permitted population-wide analyses of galaxy morphology. Morphological…

Deep neural networks (DNNs) are one of the most prominent technologies of our time, as they achieve state-of-the-art performance in many machine learning tasks, including but not limited to image classification, text mining, and speech processing. However, recent research on DNNs has indicated ever-increasing concern o…

Since the discovery of differential calculus by Newton and Leibniz and the subsequent continuous growth of its applications to physics, mechanics, geometry, etc, it was observed that partial derivatives in the study of various natural problems are (self-)organized in certain structures usually called geometric. Tensors…

Recent studies have shown that adversarial examples in state-of-the-art image classifiers trained by deep neural networks (DNN) can be easily generated when the target model is transparent to an attacker, known as the white-box setting. However, when attacking a deployed machine learning service, one can only acquire t…

We consider the groups $\operatorname{Diff}_{\mathcal B}(\mathbb R^n)$, $\operatorname{Diff}_{H^\infty}(\mathbb R^n)$, and $\operatorname{Diff}_{\mathcal S}(\mathbb R^n)$ of smooth diffeomorphisms on $\mathbb R^n$ which differ from the identity by a function which is in either $\mathcal B$ (bounded in all derivatives),…

HotNAS reduces AI search time from hundreds of GPU hours to less than 3 GPU hours.

Zeroth-order (a.k.a, derivative-free) methods are a class of effective optimization methods for solving complex machine learning problems, where gradients of the objective functions are not available or computationally prohibitive. Recently, although many zeroth-order methods have been developed, these approaches still…

A zoo of deep nets is available these days for almost any given task, and it is increasingly unclear which net to start with when addressing a new task, or which net to use as an initialization for fine-tuning a new model. To address this issue, in this paper, we develop knowledge flow which moves 'knowledge' from mult…

Datasets are growing not just in size but in complexity, creating a demand for rich models and quantification of uncertainty. Bayesian methods are an excellent fit for this demand, but scaling Bayesian inference is a challenge. In response to this challenge, there has been considerable recent work based on varying assu…

Extends coisotropic embedding theorem to various geometric settings.

The paper tackles model selection for unseen tasks by capturing relationships among checkpoints.

Clarifies the various fairness definitions in ML.

Recently, a lot of papers proposed to use neural networks to approximately solve partial differential equations (PDEs). Yet, there has been a lack of flexible framework for convenient experimentation. In an attempt to fill the gap, we introduce a PyDEns-module open-sourced on GitHub. Coupled with capabilities of BatchF…

Study classifies translating solitons in Minkowski 3-space, revealing singularities.

New unsupervised transfer learning method for spatiotemporal tasks.

Corporate bond factor research is flawed due to measurement errors and ex-post filtering.

Suppose $X$ and $Y$ are finite complexes, with $Y$ simply connected. Gromov conjectured that the number of mapping classes in $[X,Y]$ which can be realized by $L$-Lipschitz maps grows asymptotically as $L^α$, where $α$ is an integer determined by the rational homotopy type of $Y$ and the rational cohomology of $X$. Thi…

Extends ONNX for quantized neural networks with new formats and operators.

A study finds that only a few factors explain corporate bond risk, rendering extensive bond factor literature redundant.

BOAT optimizes multiple antibody properties efficiently.

We provide a detailed description of solutions of Curve Shortening in $\R^n$ that are invariant under some one-parameter symmetry group of the equation, paying particular attention to geometric properties of the curves, and the asymptotic properties of their ends. We find generalized helices, and a connection with curv…

There is an emerging trend of embedding knowledge graphs (KGs) in continuous vector spaces in order to use those for machine learning tasks. Recently, many knowledge graph embedding (KGE) models have been proposed that learn low dimensional representations while trying to maintain the structural properties of the KGs s…

DiffEqFlux.jl is a library for fusing neural networks and differential equations. In this work we describe differential equations from the viewpoint of data science and discuss the complementary nature between machine learning models and differential equations. We demonstrate the ability to incorporate DifferentialEqua…

Automates galaxy morphology classification with less human labelling.

Most network-based machine learning methods assume that the labels of two adjacent samples in the network are likely to be the same. However, assuming the pairwise relationship between samples is not complete. The information a group of samples that shows very similar pattern and tends to have similar labels is missed.…

We explain SSL objectives as log-likelihoods in a data curation model.

Let $C^{[M]}$ be a (local) Denjoy-Carleman class of Beurling or Roumieu type, where the weight sequence $M=(M_k)$ is log-convex and has moderate growth. We prove that the groups ${\operatorname{Diff}}\mathcal{B}^{[M]}(\mathbb{R}^n)$, ${\operatorname{Diff}}W^{[M],p}(\mathbb{R}^n)$, ${\operatorname{Diff}}{\mathcal{S}}{}_…

New algorithm reduces dimensionality in stochastic optimization.

Implementing large-scale deep neural networks with high computational complexity on low-cost IoT devices may inevitably be constrained by limited computation resource, making the devices hard to respond in real-time. This disjunction makes the state-of-art deep learning algorithms, i.e. CNN (Convolutional Neural Networ…

As an indispensable component, Batch Normalization (BN) has successfully improved the training of deep neural networks (DNNs) with mini-batches, by normalizing the distribution of the internal representation for each hidden layer. However, the effectiveness of BN would diminish with scenario of micro-batch (e.g., less …

Numerous methods for crafting adversarial examples were proposed recently with high success rate. Since most existing machine learning based classifiers normalize images into some continuous, real vector, domain firstly, attacks often craft adversarial examples in such domain. However, "adversarial" examples may become…

The paper introduces BCART models for aggregate claim amount, improving frequency-severity and joint modeling.

The paper uses model-based trees to create interpretable surrogate models for complex machine learning models.

Gauge Flow Models use a learnable Gauge Field in Generative Flow Models.

The study examines how model predictions hold up under model extensions.

Revises Bayesian model averaging for foundation models.

Paper introduces symmetric divergence link models for probability distributions.

New method to handle credit portfolio model uncertainties.

The paper tests stock return models and uses LSTM to predict stock returns.

Researchers review challenges in interpreting additive models, especially neural additive models.

Novel hybrid modeling combines ML and physics for real-time diagnosis.

CRS model improves ranking data modeling with theoretical guarantees.

Sigma models linked to Gross-Neveu models via quiver varieties.

Interpretable machine learning has become a strong competitor for traditional black-box models. However, the possible loss of the predictive performance for gaining interpretability is often inevitable, putting practitioners in a dilemma of choosing between high accuracy (black-box models) and interpretability (interpr…