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.
Study finds more flood risk strategies can improve outcomes in NYC.
Deep neural networks (DNNs) transform stimuli across multiple processing stages to produce representations that can be used to solve complex tasks, such as object recognition in images. However, a full understanding of how they achieve this remains elusive. The complexity of biological neural networks substantially exc…
One of the promising methods for the treatment of complex diseases such as cancer is combinational therapy. Due to the combinatorial complexity, machine learning models can be useful in this field, where significant improvements have recently been achieved in determination of synergistic combinations. In this study, we…
Signed pairwise interactions conflate uniqueness, redundancy, and synergy
Developed Taylor series for muscle-finger system analysis.
Skilled robotic manipulation benefits from complex synergies between non-prehensile (e.g. pushing) and prehensile (e.g. grasping) actions: pushing can help rearrange cluttered objects to make space for arms and fingers; likewise, grasping can help displace objects to make pushing movements more precise and collision-fr…
DL models can outperform regionalized models in hydrology by pooling diverse data.
The problem of learning a sparse model is conceptually interpreted as the process of identifying active features/samples and then optimizing the model over them. Recently introduced safe screening allows us to identify a part of non-active features/samples. So far, safe screening has been individually studied either fo…
In our study, we demonstrate the synergy effect between convolutional neural networks and the multiplicity of SMILES. The model we propose, the so-called Convolutional Neural Fingerprint (CNF) model, reaches the accuracy of traditional descriptors such as Dragon (Mauri et al. [22]), RDKit (Landrum [18]), CDK2 (Willigha…
Unified perspective unites Bayesian optimization and active learning for efficient goal-oriented optimization.
Study identifies negative data externalities affecting model performance on specific groups.
Estimates interactions between modalities for multimodal data.
PDTS improves robustness in sequential decision-making.
Enhances inverse design optimization with machine learning and reduced fidelity simulations.
Understanding how different information sources together transmit information is crucial in many domains. For example, understanding the neural code requires characterizing how different neurons contribute unique, redundant, or synergistic pieces of information about sensory or behavioral variables. Williams and Beer (…
New method disentangles high-order effects in feature importance.
In this work we present a review of the state of the art of information theoretic feature selection methods. The concepts of feature relevance, redundance and complementarity (synergy) are clearly defined, as well as Markov blanket. The problem of optimal feature selection is defined. A unifying theoretical framework i…
The paper proposes a method to estimate heterogeneous treatment effects using pretraining strategies.
Proposes a new method to better understand complex system interactions.
Combining causality, control, and reinforcement learning for system control.
New theory explains how equivariant self-supervised learning improves feature extraction.
Visual analytics systems combine machine learning or other analytic techniques with interactive data visualization to promote sensemaking and analytical reasoning. It is through such techniques that people can make sense of large, complex data. While progress has been made, the tactful combination of machine learning a…
Deep Echo State Networks (DeepESNs) recently extended the applicability of Reservoir Computing (RC) methods towards the field of deep learning. In this paper we study the impact of constrained reservoir topologies in the architectural design of deep reservoirs, through numerical experiments on several RC benchmarks. Th…
Study maps interdependence of SDGs, finds complex, dynamic linkages.
The matrix-based Renyi's α-entropy functional and its multivariate extension were recently developed in terms of the normalized eigenspectrum of a Hermitian matrix of the projected data in a reproducing kernel Hilbert space (RKHS). However, the utility and possible applications of these new estimators are rather new an…
Study presents a low-cost local motion planner for vineyard navigation.
The intrinsic error tolerance of neural network (NN) makes approximate computing a promising technique to improve the energy efficiency of NN inference. Conventional approximate computing focuses on balancing the efficiency-accuracy trade-off for existing pre-trained networks, which can lead to suboptimal solutions. In…
Independent component analysis (ICA) is a powerful method for blind source separation based on the assumption that sources are statistically independent. Though ICA has proven useful and has been employed in many applications, complete statistical independence can be too restrictive an assumption in practice. Additiona…
Memorizing rare examples helps neural networks generalize better.
Data mining revealed a cluster of economic, psychological, social and cultural indicators that in combination predicted corruption and wealth of European nations. This prosperity syndrome of self-reliant citizens, efficient division of labor, a sophisticated scientific community, and respect for the law, was clearly di…
Matrix multiplication is a fundamental building block for large scale computations arising in various applications, including machine learning. There has been significant recent interest in using coding to speed up distributed matrix multiplication, that are robust to stragglers (i.e., machines that may perform slower …
Machine learning advances chemistry and materials science by enabling large-scale exploration of chemical space based on quantum chemical calculations. While these models supply fast and accurate predictions of atomistic chemical properties, they do not explicitly capture the electronic degrees of freedom of a molecule…
The purpose of the New York Workshop on Computer, Earth and Space Sciences is to bring together the New York area's finest Astronomers, Statisticians, Computer Scientists, Space and Earth Scientists to explore potential synergies between their respective fields. The 2011 edition (CESS2011) was a great success, and we w…
This work shows how disentangled and sparse representations improve multi-task learning.
MTRGL learns temporal correlations from multi-modal data for improved pair trading.
We propose a reinforcement learning framework for discrete environments in which an agent makes both strategic and tactical decisions. The former manifests itself through the use of value function, while the latter is powered by a tree search planner. These tools complement each other. The planning module performs a lo…
The paper studies degenerate and nonlocal elliptic operators on Poincaré-Einstein manifolds.
Research adapts Multi-Armed Bandits for Minesweeper, improving player strategy.
Combining complementary information from multiple modalities is intuitively appealing for improving the performance of learning-based approaches. However, it is challenging to fully leverage different modalities due to practical challenges such as varying levels of noise and conflicts between modalities. Existing metho…
The task of classifying X-ray data is a problem of both theoretical and clinical interest. Whilst supervised deep learning methods rely upon huge amounts of labelled data, the critical problem of achieving a good classification accuracy when an extremely small amount of labelled data is available has yet to be tackled.…
The main goal of this paper is presentation a modern axiomatic approach to financial arithmetic. At the first, the axiomatic financial arithmetic theory was proposed by Peccati who has introduced the axiomatic definition of the future value. This theory has been extensively developed in past years. Proposed approach to…
NNs can learn efficient algorithms for certain problems.
MathChat uses LLM agents to solve challenging math problems through conversational problem-solving.
New method improves RL in continuous spaces with kernel smoothing.
New metric for disentangling multivariate representations, accounting for more complex entanglements.
Improved diffusion models using energy distillation and sequential Monte Carlo.
This study compares CeFi and DeFi, finding some DeFi assets are not truly decentralized.
TSC uses HMC and adaptive transport maps to optimize forward KL for variational inference.