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.
The study tackles forgery in machine unlearning, showing that forging is limited and can be detected.
Manipulating video content is easier than ever. Due to the misuse potential of manipulated content, multiple detection techniques that analyze the pixel data from the videos have been proposed. However, clever manipulators should also carefully forge the metadata and auxiliary header information, which is harder to do …
In this paper we construct an infinite family of homotopically rigid spaces. These examples are then used as building blocks to forge highly connected rational spaces with prescribed finite group of self-homotopy equivalences. They are also exploited to provide highly connected inflexible and strongly chiral manifolds.
Interpool solves interoperability issues by minting, exchanging, and burning tokens within a single liquidity pool.
A random forest is a popular tool for estimating probabilities in machine learning classification tasks. However, the means by which this is accomplished is unprincipled: one simply counts the fraction of trees in a forest that vote for a certain class. In this paper, we forge a connection between random forests and ke…
The paper explains the importance of diffeological groupoids in modern geometry and physics.
This paper investigates a class of attacks targeting the confidentiality aspect of security in Deep Reinforcement Learning (DRL) policies. Recent research have established the vulnerability of supervised machine learning models (e.g., classifiers) to model extraction attacks. Such attacks leverage the loosely-restricte…
Paper interprets UMAP and t-SNE as probabilistic MAP inference.
Motivation: Cell-biological processes are regulated through a complex network of interactions between genes and their products. The processes, their activating conditions, and the associated transcriptional responses are often unknown. Organism-wide modeling of network activation can reveal unique and shared mechanisms…
Astronomy of the 21st century increasingly finds itself with extreme quantities of data. This growth in data is ripe for modern technologies such as deep image processing, which has the potential to allow astronomers to automatically identify, classify, segment and deblend various astronomical objects. In this paper, w…
We show that wave maps from two-dimensional Minkowski space to hyperbolic spaces $\H^m$ are globally smooth in time if the initial data is smooth, conditionally on some reasonable claims concerning the local theory of such wave maps, as well as the self-similar and travelling (or stationary solutions); w…
Optimizes target value in stochastic black box functions.
Modern audio source separation techniques rely on optimizing sequence model architectures such as, 1D-CNNs, on mixture recordings to generalize well to unseen mixtures. Specifically, recent focus is on time-domain based architectures such as Wave-U-Net which exploit temporal context by extracting multi-scale features. …
This paper connects geometric diagrams to spherical T-duality.
Asynchronous methods are widely used in deep learning, but have limited theoretical justification when applied to non-convex problems. We show that running stochastic gradient descent (SGD) in an asynchronous manner can be viewed as adding a momentum-like term to the SGD iteration. Our result does not assume convexity …
Develops Weil bundles over \( p \)-adic manifolds for arithmetic geometry.
VQShape learns interpretable time-series representations and achieves comparable performance to specialist models.
We suggest a new optimization technique for minimizing the sum of non-convex real functions that satisfy a property that we call piecewise log-Lipschitz. This is by forging links between techniques in computational geometry, combinatorics and convex optimization. As an example application, we …
Despite their tremendous success in a range of domains, deep learning systems are inherently susceptible to two types of manipulations: adversarial inputs -- maliciously crafted samples that deceive target deep neural network (DNN) models, and poisoned models -- adversely forged DNNs that misbehave on pre-defined input…
Transformers can emulate various algorithms by prompting, proving universality.
We use partial class memberships in soft classification to model uncertain labelling and mixtures of classes. Partial class memberships are not restricted to predictions, but may also occur in reference labels (ground truth, gold standard diagnosis) for training and validation data. Classifier performance is usually ex…
New framework tackles deep financial reporting bottleneck by improving hallucination and coherence.
This monograph deals with adaptive supervised classification, using tools borrowed from statistical mechanics and information theory, stemming from the PACBayesian approach pioneered by David McAllester and applied to a conception of statistical learning theory forged by Vladimir Vapnik. Using convex analysis on the se…
This work proposes a novel method for interpolating ROMs without solving FEM models.