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.
This paper provides a neural approach to represent option implied information.
Minimalist softmax attention learns constrained Boolean functions with supervision.
MINTS uses a minimalist Bayesian framework to tackle multi-armed bandits with structural constraints.
Minimalistic model captures head direction system properties.
A minimalist approach generates synthetic tabular data with sparse PCA and XGBoost.
A minimalist approach improves LLM reasoning by filtering incorrect responses.
A new Bayesian framework simplifies stochastic optimization by focusing on key parameters.
Minimalistic unsupervised learning with sparse manifold transform achieves SOTA performance.
Classifiers for the semi-supervised setting often combine strong supervised models with additional learning objectives to make use of unlabeled data. This results in powerful though very complex models that are hard to train and that demand additional labels for optimal parameter tuning, which are often not given when …
We study a minimalist kinetic model for economies. A system of agents with local trading rules display emergent demand behaviour. We examine the resulting wealth distribution to look for non-thermal behaviour. We compare and contrast this model with other similar models.
GMC benchmark isolates retrieval in Transformers, revealing max-margin alignment.
MINIMALIST maximizes mutual information for likelihood estimation from simulated data.
Recent studies have revealed that neural network-based policies can be easily fooled by adversarial examples. However, while most prior works analyze the effects of perturbing every pixel of every frame assuming white-box policy access, in this paper we take a more restrictive view towards adversary generation - with t…
Motion planning and control are key problems in a collection of robotic applications including the design of autonomous agile vehicles and of minimalist manipulators. These problems can be accurately formalized within the language of affine connections and of geometric control theory. In this paper we overview recent r…
Study on how sampling works for complex data functions.
Hyperbolic geometry autoencoder outperforms Euclidean in top-N recommendation tasks.
Sum-Product Networks (SPNs) are a class of expressive yet tractable hierarchical graphical models. LearnSPN is a structure learning algorithm for SPNs that uses hierarchical co-clustering to simultaneously identifying similar entities and similar features. The original LearnSPN algorithm assumes that all the variables …
New model predicts time-varying interactions in complex systems.
Wealth inequality is an important matter for economic theory and policy. Ongoing debates have been discussing recent rise in wealth inequality in connection with recent development of active financial markets around the world. Existing literature on wealth distribution connects the origins of wealth inequality with a v…
We define On-Average KL-Privacy and present its properties and connections to differential privacy, generalization and information-theoretic quantities including max-information and mutual information. The new definition significantly weakens differential privacy, while preserving its minimalistic design features such …
We introduce and study a simple model of a limit order-driven market. Traders in this model can either trade at the market price or place a limit order, i.e. an instruction to buy (sell) a certain amount of the stock if its price falls below (raises above) a predefined level. The choice between these two options is pur…
NCP uses neural networks to efficiently learn conditional distributions.
There is growing evidence regarding the importance of spike timing in neural information processing, with even a small number of spikes carrying information, but computational models lag significantly behind those for rate coding. Experimental evidence on neuronal behavior is consistent with the dynamical and state dep…
You are a financial analyst. At the beginning of every week, you are able to rank every pair of stochastic processes starting from that week up to the horizon. Suppose that two processes are equal at the beginning of the week. Your ranking procedure is time consistent if the ranking does not change between this week an…
Model compares altruism and individualism in wealth dynamics.
In this paper we propose a fusion approach to continuous emotion recognition that combines visual and auditory modalities in their representation spaces to predict the arousal and valence levels. The proposed approach employs a pre-trained convolution neural network and transfer learning to extract features from video …
Predictive Sparse Manifold Transform learns dynamic video sequences.
We aim to develop off-policy DRL algorithms that not only exceed state-of-the-art performance but are also simple and minimalistic. For standard continuous control benchmarks, Soft Actor-Critic (SAC), which employs entropy maximization, currently provides state-of-the-art performance. We first demonstrate that the entr…
A new deep learning benchmark reduces resource needs.
A simple approach to offline RL without additional complexity.
A simple function shows how neural nets can converge despite high sharpness.
We consider the performance of the bootstrap in high-dimensions for the setting of linear regression, where but is not close to zero. We consider ordinary least-squares as well as robust regression methods and adopt a minimalist performance requirement: can the bootstrap give us good confidence intervals fo…
New method designs antimicrobial peptides with high potency and low toxicity.
A great variety of text tasks such as topic or spam identification, user profiling, and sentiment analysis can be posed as a supervised learning problem and tackle using a text classifier. A text classifier consists of several subprocesses, some of them are general enough to be applied to any supervised learning proble…
Machine learning models predict which ideas will be innovated based on subjective perspectives.
New approach to convex hulls for low-rank problems.
This paper introduces a new perspective on multi-class ensemble classification that considers training an ensemble as a state estimation problem. The new perspective considers the final ensemble classifier model as a static state, which can be estimated using a Kalman filter that combines noisy estimates made by indivi…
A new approach for learning from expert demonstrations using multiple perspectives.
Smooth metric measure spaces have been studied from the two different perspectives of Bakry-Émery and Chang-Gursky-Yang, both of which are closely related to work of Perelman on the Ricci flow. These perspectives include a generalization of the Ricci curvature and the associated quasi-Einstein metrics, which include Ei…
In this paper, we perform a minimalistic quantization of the classical game of tic-tac-toe, by allowing superpositions of classical moves. In order for the quantum game to reduce properly to the classical game, we require legal quantum moves to be orthogonal to all previous moves. We also admit interference effects, by…
A new method interprets astrophysical spectra using geometric paths to distinguish line profiles.
New MCMC method improves sampling efficiency across diverse structural models.
Paper classifies institutions based on credit, debit, and funding adjustment paradigms.
Currently, there starts a research trend to leverage neural architecture for recommendation systems. Though several deep recommender models are proposed, most methods are too simple to characterize users' complex preference. In this paper, for a fine-grain analysis, users' ratings are explained from multiple perspectiv…
Survey explores translation surfaces from geometric and topological perspectives.
This work analyzes tree-based methods from a ranking perspective, providing insights and new statistics.
The present, partly expository, monograph consists of three parts. The first part treats Spin- and Pin-structures from three different perspectives and shows them to be suitably equivalent. It also introduces an intrinsic perspective on the relative Spin- and Pin-structures of Fukaya-Oh-Ohta-Ono and Solomon, establishe…
This paper analyzes self-supervised learning from a multi-view perspective.