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.
Forward-prediction models enhance physical reasoning, but only for specific tasks.
PBI inference may not be calibrated if predictive model is inaccurate.
KINet learns object interactions without supervision for robotic pushing.
This paper presents a new meta-modeling framework to employ deep reinforcement learning (DRL) to generate mechanical constitutive models for interfaces. The constitutive models are conceptualized as information flow in directed graphs. The process of writing constitutive models are simplified as a sequence of forming g…
In this paper we consider self-supervised representation learning to improve sample efficiency in reinforcement learning (RL). We propose a forward prediction objective for simultaneously learning embeddings of states and action sequences. These embeddings capture the structure of the environment's dynamics, enabling e…
We propose a new model for unsupervised document embedding. Leading existing approaches either require complex inference or use recurrent neural networks (RNN) that are difficult to parallelize. We take a different route and develop a convolutional neural network (CNN) embedding model. Our CNN architecture is fully par…
Reinforcement learning algorithms struggle when the reward signal is very sparse. In these cases, naive random exploration methods essentially rely on a random walk to stumble onto a rewarding state. Recent works utilize intrinsic motivation to guide the exploration via generative models, predictive forward models, or …
A dry decade in the Navajo Nation has killed vegetation, dessicated soils, and released once-stable sand into the wind. This sand now covers one-third of the Nation's land, threatening roads, gardens and hundreds of homes. Many arid regions have similar problems: global warming has increased dune movement across farmla…
This paper examines foreign exchange risk premia from simple univariate regressions to the state-space method. The adjusted traditional regressions properly figure out the existence and time-evolving property of the risk premia. Successively, the state-space estimations overall are quite rationally competent in examini…
Deep reinforcement learning approaches have shown impressive results in a variety of different domains, however, more complex heterogeneous architectures such as world models require the different neural components to be trained separately instead of end-to-end. While a simple genetic algorithm recently showed end-to-e…
Adjoint SA speeds up bioprocess parameter learning.
We present an extension of our Molecular Transformer architecture combined with a hyper-graph exploration strategy for automatic retrosynthesis route planning without human intervention. The single-step retrosynthetic model sets a new state of the art for predicting reactants as well as reagents, solvents and catalysts…
A VAE model predicts material properties and microstructures.
Study uses AI and ML to predict and optimize corrosion resistance of aluminum alloys.
Gradient guidance improves diffusion models for optimizing specific objectives.
Unified framework for forward and inverse PDE problems in multiphase media.
Two methods forecast functional time series, offering competitive results.
iGNN tackles inverse graph prediction using invertible neural networks.
Paper proposes hybrid modeling to improve surrogate accuracy using multiple data sources.
This review is a partial synthesis of the book ``Why stock market crash'' (Princeton University Press, January 2003), which presents a general theory of financial crashes and of stock market instabilities that his co-workers and the author have developed over the past seven years. The study of the frequency distributio…
We propose a novel method to forecast the future from the present using time-reversed data.