arXiv research

Butterfly tackles wild unsupervised domain adaptation with noisy labeled data.

The purpose of this paper is to construct an example of a 2-knot wildly embedded in $\mathbb{S}^{4}$ as the limit set of a Kleinian group. We find that this type of wild 2-knots has very interesting topological properties.

In this article we prove that, for an oriented PL $n$-manifold $M$ with $m$ boundary components and $d_0\in \mathbb N$, there exist mutually disjoint closed Euclidean balls and a $\mathsf K$-quasiregular mapping $M \to \mathbb S^n \setminus \mathrm{int}(B_1\cup \cdots \cup B_m)$ of degree at least $d_0$. The result is …

In the current environment of financial distress, many governments are likely to soon become major holders of financial assets, but the policy debate focuses only on the likelihood and extent of short-term market stabilization. This paper shows that government intervention and propping up are likely to lead to long-ter…

The author has elsewhere given a complete classification of those compact oriented Einstein 4-manifolds on which the self-dual Weyl curvature is everywhere positive in the direction of some self-dual harmonic 2-form. In this article, similar results are obtained when the self-dual Weyl curvature is everywhere non-negat…

Stock markets show unusual overnight and intraday returns.

We give a rigorous analysis of the statistical behavior of gradients in a randomly initialized fully connected network N with ReLU activations. Our results show that the empirical variance of the squares of the entries in the input-output Jacobian of N is exponential in a simple architecture-dependent constant beta, gi…

Paper defines predictive multiplicity and measures its severity in classification problems.

Deep generative models have been wildly successful at learning coherent latent representations for continuous data such as video and audio. However, generative modeling of discrete data such as arithmetic expressions and molecular structures still poses significant challenges. Crucially, state-of-the-art methods often …

A risk-neutral method is always used to price and hedge contingent claims in complete market, but another method based on utility maximization or risk minimization is wildly used in more general case. One can find all kinds of special risk measure in literature. In this paper, instead of using market modified risk meas…

The study extends Huber's theorem to higher dimensions with curvature constraints.

We extend in a minimal way the stylized model introduced in in "Tipping Points in Macroeconomic Agent Based Models" [JEDC 50, 29-61 (2015)], with the aim of investigating the role and efficacy of monetary policy of a `Central Bank' that sets the interest rate such as to steer the economy towards a prescribed inflation …

Revisits the connection between neural networks and the Kolmogorov-Arnold theorem.

New framework explains deep learning using signal processing techniques.

Rank minimization (RM) is a wildly investigated task of finding solutions by exploiting low-rank structure of parameter matrices. Recently, solving RM problem by leveraging non-convex relaxations has received significant attention. It has been demonstrated by some theoretical and experimental work that non-convex relax…

Theoretical analysis improves understanding of Deep Q-Learning's behavior.

We develop a model for contagion in reinsurance networks by which primary insurers' losses are spread through the network. Our model handles general reinsurance contracts, such as typical excess of loss contracts. We show that simpler models existing in the literature--namely proportional reinsurance--greatly underesti…

Unsupervised classification methods learn a discriminative classifier from unlabeled data, which has been proven to be an effective way of simultaneously clustering the data and training a classifier from the data. Various unsupervised classification methods obtain appealing results by the classifiers learned in an uns…

Improves deep RL agents' generalization to unseen environments.

Unsupervised learning models can produce accurate but misleading predictions.

Enhances neural networks with prior function values to improve accuracy.

Causal influence measures for machine learnt classifiers shed light on the reasons behind classification, and aid in identifying influential input features and revealing their biases. However, such analyses involve evaluating the classifier using datapoints that may be atypical of its training distribution. Standard me…

We consider orientation-preserving actions of a finite group G on the 3-sphere S^3 (and also on Euclidean space R^3). By the geometrization of finite group actions on 3-manifolds, if such an action is smooth then it is conjugate to an orthogonal action, and in particular G is isomorphic to a subgroup of the orthogonal …

Study on market instability in multi-agent trading with price impact and transaction costs.

A novel unsupervised outlier detection method using Randomized PCA Forest.

Unsupervised machine translation---i.e., not assuming any cross-lingual supervision signal, whether a dictionary, translations, or comparable corpora---seems impossible, but nevertheless, Lample et al. (2018) recently proposed a fully unsupervised machine translation (MT) model. The model relies heavily on an adversari…

Paper proposes BTuD for unsupervised feature selection.

This research shows unsupervised GANs can perform object segmentation without labels.

Unified framework for analyzing neural networks trained by gradient descent.

Paper proposes a novel unsupervised feature selection method using K-means and ADMM.

Unsupervised ensemble classification for dependent data.

Paper proposes a new unsupervised clustering method using attention models.

Paper presents a workflow for reliable unsupervised learning in science.

We introduce a framework to leverage knowledge acquired from a repository of (heterogeneous) supervised datasets to new unsupervised datasets. Our perspective avoids the subjectivity inherent in unsupervised learning by reducing it to supervised learning, and provides a principled way to evaluate unsupervised algorithm…

The authors advocate for more rigorous unsupervised cross-lingual learning methods.

The paper shows how integrating categorical semantics can enhance unsupervised domain translation.

Improved unsupervised anomaly detection using Random Forest.

End-to-end training solves deep unsupervised contrastive learning problems.

A new ML method predicts long-time-step molecular dynamics, preserving symplectic and time-reversible properties.

Proposes a new model for unsupervised clustering with latent variables.

Minimal variations guide unsupervised learning for better downstream tasks.

Recently, multilayer bootstrap network (MBN) has demonstrated promising performance in unsupervised dimensionality reduction. It can learn compact representations in standard data sets, i.e. MNIST and RCV1. However, as a bootstrap method, the prediction complexity of MBN is high. In this paper, we propose an unsupervis…

Study proposes using auxiliary classification to improve unsupervised anomaly detection.

Paper summarizes unsupervised learning challenges for disentangled representations.

MLPerf benchmarks ML inference systems across diverse hardware.

This paper proves the theoretical advantage of unsupervised pretraining for machine learning tasks.

New framework uses unsupervised learning for efficient exploration in RL.

New unsupervised feature selection method for imbalanced datasets.