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 constructs a transfer map for codimension 2 submanifolds in higher index theory.
We consider a transfer-learning problem by using the parameter transfer approach, where a suitable parameter of feature mapping is learned through one task and applied to another objective task. Then, we introduce the notion of the local stability and parameter transfer learnability of parametric feature mapping,and th…
We record various properties of twisted Becker-Gottlieb transfer maps and study their multiplicative properties analogous to Becker-Gottlieb transfer. We show these twisted transfer maps factorise through Becker-Schultz-Mann-Miller-Miller transfer; some of these might be well known. We apply this to show that $BSO(2n+1…
To reduce the large computation and storage cost of a deep convolutional neural network, the knowledge distillation based methods have pioneered to transfer the generalization ability of a large (teacher) deep network to a light-weight (student) network. However, these methods mostly focus on transferring the probabili…
We extend Jendrol' and Skupień's results about the local structure of maps on the 2-sphere: In this paper we show that if a polyhedral map on a surface $\M$ of Euler characteristic $χ(\M) \le 0$ has more than $126|χ(\M)|$ vertices, then has a vertex with "nearly" non-negative combinatorial curvature. As a corol…
In this work, we ask the following question: Can visual analogies, learned in an unsupervised way, be used in order to transfer knowledge between pairs of games and even play one game using an agent trained for another game? We attempt to answer this research question by creating visual analogies between a pair of game…
In this paper, we propose a novel learning framework for the problem of domain transfer learning. We map the data of two domains to one single common space, and learn a classifier in this common space. Then we adapt the common classifier to the two domains by adding two adaptive functions to it respectively. In the com…
Weight Squeezing transfers knowledge from large models to smaller ones, improving performance and speed.
A new method estimates generative model mappings using kernel transfer operators, reducing costs and improving performance.
We develop differential algebraic K-theory for rings of integers in number fields and we construct a cycle map from geometrized bundles of modules over such a ring to the differential algebraic K-theory. We also treat some of the foundational aspects of differential cohomology, including differential function spectra a…
Transfer learning through fine-tuning a pre-trained neural network with an extremely large dataset, such as ImageNet, can significantly accelerate training while the accuracy is frequently bottlenecked by the limited dataset size of the new target task. To solve the problem, some regularization methods, constraining th…
Researchers prove an -theoretic signature transfer in codimension 2.
Designs a framework to transfer causal models between similar environments.
Researchers in functional neuroimaging mostly use activation coordinates to formulate their hypotheses. Instead, we propose to use the full statistical images to define regions of interest (ROIs). This paper presents two machine learning approaches, transfer learning and selection transfer, that are compared upon their…
Method learns feature map between source and target domains for high-dimensional regression with missing features.
JSCN improves cross-domain recommendation by learning domain-invariant user representations.
We propose Gaussian optimal transport for Image style transfer in an Encoder/Decoder framework. Optimal transport for Gaussian measures has closed forms Monge mappings from source to target distributions. Moreover interpolates between a content and a style image can be seen as geodesics in the Wasserstein Geometry. Usi…
Continuity of earthquake flow map transfers Teichmüller dynamics results.
Paper explores using bi-fidelity data to train neural networks for uncertainty quantification.
Proposes m-POT to improve m-OT's misspecified mappings issue.
This research evaluates learning models for bionic robots, focusing on transfer function identification.
ActiLabel learns activity patterns across diverse sensor devices.
In this paper, we present a new approach to Transfer Learning (TL) in Reinforcement Learning (RL) for cross-domain tasks. Many of the available techniques approach the transfer architecture as a method of speeding up the target task learning. We propose to adapt and reuse the mapped source task optimal-policy directly …
MPHD transfers knowledge across different domains for Bayesian optimization.
New methods avoid spectral pollution in transfer operators for accurate analysis.
This paper proposes an online knowledge distillation method that transfers feature map information in addition to class probabilities.
Neural networks are vulnerable to adversarial examples, malicious inputs crafted to fool trained models. Adversarial examples often exhibit black-box transfer, meaning that adversarial examples for one model can fool another model. However, adversarial examples are typically overfit to exploit the particular architectu…
In this paper, we study the problem of transfer learning with the attribute data. In the transfer learning problem, we want to leverage the data of the auxiliary and the target domains to build an effective model for the classification problem in the target domain. Meanwhile, the attributes are naturally stable cross d…
End-to-end algorithm for W-2 distance using neural networks.
This paper provides a rational model for fiberwise THH transfer using A-infinity algebras.
The cross-domain recommendation technique is an effective way of alleviating the data sparse issue in recommender systems by leveraging the knowledge from relevant domains. Transfer learning is a class of algorithms underlying these techniques. In this paper, we propose a novel transfer learning approach for cross-doma…
TMDA aligns subdomain data distribution discrepancies across domains using manifold representations.
BAR reprograms black-box ML models for transfer learning with scarce data.
OpFlow predicts robust OD flows by learning choice potentials conditioned on spatial exposures.
Anosov maps study with new Banach space and foliation method.
A new method for hyperparameter tuning across multiple datasets and objectives.
SF-DQN improves RL transfer by learning successor features.
BeST metric selects best source models for transfer learning.
Deep Neural Networks have been found vulnerable re-cently. A kind of well-designed inputs, which called adver-sarial examples, can lead the networks to make incorrectpredictions. Depending on the different scenarios, goalsand capabilities, the difficulties of the attacks are different.For example, a targeted attack is …
Deep learning speeds up protein mapping entropy calculation.
Method maps imperfect simulations to observed stellar spectra using unsupervised domain adaptation.
The circle transfer has appeared in several contexts in topology. In this note we observe that this map admits a geometric re-interpretation as a morphism of cobordism categories of 0-manifolds and 1-cobordisms. Let denote the 1-dimensional cobordism category and let $Circ(X) \subse…
Domain adaptation leverages the knowledge in one domain - the source domain - to improve learning efficiency in another domain - the target domain. Existing heterogeneous domain adaptation research is relatively well-progressed, but only in situations where the target domain contains at least a few labeled instances. I…
Unified framework maps financial market dynamics using TE and KM, revealing directional information flow.
Zero-shot KD for object detection without training data.
A new model SEQ clusters and classifies encoded features for better interpretability.
Notes on quasiregular maps between Riemannian manifolds, preserving Sobolev forms.
This short note highlights some links between two lines of research within the emerging topic of trustworthy machine learning: differential privacy and robustness to adversarial examples. By abstracting the definitions of both notions, we show that they build upon the same theoretical ground and hence results obtained …