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.
Paper relaxes symmetry conditions for universal feature selection in noisy data.
We study the approximation properties of random ReLU features through their reproducing kernel Hilbert space (RKHS). We first prove a universality theorem for the RKHS induced by random features whose feature maps are of the form of nodes in neural networks. The universality result implies that the random ReLU features…
The study proves Gaussian universality of deep random features learning.
The paper identifies universal features for high-dimensional data inference.
UniFeat is an open-source Java tool for feature selection.
Quantum kernels can be efficiently embedded into classical feature spaces.
Quantum machine learning models can approximate any continuous function.
Path signatures adapted for Lie groups improve action recognition in computer vision.
USFs capture dynamics for faster RL task transfer.
Unified theorem for deep and shallow joint-equivariant machines.
Random feature models approximate functions in Banach spaces efficiently.
Phishing as one of the most well-known cybercrime activities is a deception of online users to steal their personal or confidential information by impersonating a legitimate website. Several machine learning-based strategies have been proposed to detect phishing websites. These techniques are dependent on the features …
Effective feature representation is key to the predictive performance of any algorithm. This paper introduces a meta-procedure, called Non-Euclidean Upgrading (NEU), which learns feature maps that are expressive enough to embed the universal approximation property (UAP) into most model classes while only outputting fea…
New insights into model robustness for random features and NTK models.
Transformers enable in-context learning with guarantees for a wide range of tasks.
In the framework of Lorentzian warped products, we study the Friedmann-Robertson-Walker cosmological model to investigate non-smooth curvatures associated with multiple discontinuities involved in the evolution of the universe. In particular we analyze non-smooth features of the spatially flat Friedmann-Robertson-Walke…
A new neural network framework ADNN improves financial feature construction.
In this paper, we show how novel transfer reinforcement learning techniques can be applied to the complex task of target driven navigation using the photorealistic AI2THOR simulator. Specifically, we build on the concept of Universal Successor Features with an A3C agent. We introduce the novel architectural contributio…
We analyze the constituents stocks of the Dow Jones Industrial Average (DJIA30) and the Standard & Poor's 100 index (S&P100) of the NYSE stock exchange market. Surprisingly, we discover the data collapse of the histograms of the DJIA30 price fluctuations and of the S&P100 price fluctuations to the universal non-paramet…
Identifying small subsets of features that are relevant for prediction and/or classification tasks is a central problem in machine learning and statistics. The feature selection task is especially important, and computationally difficult, for modern datasets where the number of features can be comparable to, or even ex…
Max-margin classifiers' behavior is studied in high dimensions with non-Gaussian features.
We propose a novel nonparametric online predictor for discrete labels conditioned on multivariate continuous features. The predictor is based on a feature space discretization induced by a full-fledged k-d tree with randomly picked directions and a recursive Bayesian distribution, which allows to automatically learn th…
We propose semi-random features for nonlinear function approximation. The flexibility of semi-random feature lies between the fully adjustable units in deep learning and the random features used in kernel methods. For one hidden layer models with semi-random features, we prove with no unrealistic assumptions that the m…
GNNs with random node initialization are shown to be universally expressive.
A practical limitation of deep neural networks is their high degree of specialization to a single task and visual domain. Recently, inspired by the successes of transfer learning, several authors have proposed to learn instead universal, fixed feature extractors that, used as the first stage of any deep network, work w…
We introduce features for massive data streams. These stream features can be thought of as "ordered moments" and generalize stream sketches from "moments of order one" to "ordered moments of arbitrary order". In analogy to classic moments, they have theoretical guarantees such as universality that are important for lea…
Deep random feature models are analyzed for their performance with exact asymptotic expressions.
The study of linguistic typology is rooted in the implications we find between linguistic features, such as the fact that languages with object-verb word ordering tend to have post-positions. Uncovering such implications typically amounts to time-consuming manual processing by trained and experienced linguists, which p…
New method generates diverse EHR data types while maintaining privacy.
Adaptive GPR-GNN optimizes node feature and topology learning.
URT layer improves few-shot image classification across diverse domains.
The ability of a reinforcement learning (RL) agent to learn about many reward functions at the same time has many potential benefits, such as the decomposition of complex tasks into simpler ones, the exchange of information between tasks, and the reuse of skills. We focus on one aspect in particular, namely the ability…
New conditions ensure deep neural networks can approximate any function on non-Euclidean spaces.
Gaussian equivalence fails for simple polynomial embeddings in quadratic scaling RF models.
New findings show Gaussian universality breaks down in high-dimensional linear factor mixtures.
New method renormalizes neural network Gaussian processes to identify learnable vs. unlearnable modes.
Universal supervised learning is considered from an information theoretic point of view following the universal prediction approach, see Merhav and Feder (1998). We consider the standard supervised "batch" learning where prediction is done on a test sample once the entire training data is observed, and the individual s…
PanRep learns universal node embeddings for heterogeneous graphs.
Signature portfolios approximate optimal wealth in non-Markovian markets.
Transfer learning and data augmentation improve stock classification performance.
Implementing -NN classification using Gromov--Wasserstein distances
In this work we show that, using the eigen-decomposition of the adjacency matrix, we can consistently estimate feature maps for latent position graphs with positive definite link function , provided that the latent positions are i.i.d. from some distribution F. We then consider the exploitation task of vertex classi…
SAGE quantifies feature importance in machine learning models.
We introduce a new feature map for barcodes that arise in persistent homology computation. The main idea is to first realize each barcode as a path in a convenient vector space, and to then compute its path signature which takes values in the tensor algebra of that vector space. The composition of these two operations …
Adversarially trained transformers can learn robustly across tasks with minimal tuning.
Accurate approximations to density functionals have recently been obtained via machine learning (ML). By applying ML to a simple function of one variable without any random sampling, we extract the qualitative dependence of errors on hyperparameters. We find universal features of the behavior in extreme limits, includi…
This short report describes our submission to the ISIC 2018 Challenge in Skin Lesion Analysis Towards Melanoma Detection for Task1 and Task 3. This work has been accomplished by a team of researchers at the University of Dayton Signal and Image Processing Lab. Our proposed approach is computationally efficient are comb…
This study approximates neural network features for modeling relations and attention mechanisms.