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.
New approach improves adversarial robustness without sacrificing natural generalization.
Clarinet uses complementary labels to train classifiers with less source data.
arfpy simplifies data generation with adversarial random forests.
Spider GAN accelerates GAN training with a new approach.
Financial decisions impact our lives, and thus everyone from the regulator to the consumer is interested in fair, sound, and explainable decisions. There is increasing competitive desire and regulatory incentive to deploy AI mindfully within financial services. An important mechanism towards that end is to explain AI d…
A new, computationally friendly formula for a class of risk-averse preferences.
The notion of friendliness between trees first appeared in solution of Lando's problem on intersection of polyhedra in 3-space. A tree is friendly to a path graph if edges of the tree can be numbered so that for each k,s the path between the edges k and k+1 contains either both or none of the edges k+2s,k+2s+1. Theorem…
Researchers develop methods to prevent GANs from generating certain types of images.
A new method improves adversarial robustness and interpretability with reduced training time.
Paper speeds up large foundation models for time series data.
Paper improves KNN-Shapley for privacy-friendly data valuation.
We formally prove the connection between k-means clustering and the predictions of neural networks based on the softmax activation layer. In existing work, this connection has been analyzed empirically, but it has never before been mathematically derived. The softmax function partitions the transformed input space into…
We introduce a mathematician-friendly formulation of the physicist-friendly derivation of the Atiyah-Patodi-Singer index of our previous paper. Our viewpoint sheds some new light on the interplay among the Atiyah-Patodi-Singer boundary condition, domain-wall fermions, and edge modes.
Root Cause Analysis for Anomalies is challenging because of the trade-off between the accuracy and its explanatory friendliness, required for industrial applications. In this paper we propose a framework for simple and friendly RCA within the Bayesian regime under certain restrictions (that Hessian at the mode is diago…
New algorithms adapt to friendly environments in online learning.
Historically, machine learning in computer security has prioritized defense: think intrusion detection systems, malware classification, and botnet traffic identification. Offense can benefit from data just as well. Social networks, with their access to extensive personal data, bot-friendly APIs, colloquial syntax, and …
This paper focuses on coordinate update methods, which are useful for solving problems involving large or high-dimensional datasets. They decompose a problem into simple subproblems, where each updates one, or a small block of, variables while fixing others. These methods can deal with linear and nonlinear mappings, sm…
Unified techniques improve stability and replicability in changing data.
Photovoltaic systems have been widely deployed in recent times to meet the increased electricity demand as an environmental-friendly energy source. The major challenge for integrating photovoltaic systems in power systems is the unpredictability of the solar power generated. In this paper, we analyze the impact of havi…
The Atiyah-Patodi-Singer index theorem describes the bulk-edge correspondence of symmetry protected topological insulators. The mathematical setup for this theorem is, however, not directly related to the physical fermion system, as it imposes on the fermion fields a non-local and unnatural boundary condition known as …
Big data is one of the cornerstones to enabling and training deep neural networks (DNNs). Because of the lack of expertise, to gain benefits from their data, average users have to rely on and upload their private data to big data companies they may not trust. Due to the compliance, legal, or privacy constraints, most u…
We describe the cohomology ring of the moduli space of a flexible polygon in geometrically meaningful terms. We propose two presentations, both are computation friendly: there are simple rules for cup product.
Advocates for user-friendly RL problem descriptions to improve usability and generalization.
TRUST improves tree models' accuracy while maintaining interpretability.
We propose a model-based machine-learning approach for polarization-multiplexed systems by parameterizing the split-step method for the Manakov-PMD equation. This approach performs hardware-friendly DBP and distributed PMD compensation with performance close to the PMD-free case.
A simplified, user-friendly repackaging of the curvature estimates implied by the Seiberg-Witten equations is formulated in terms of the convex hull of the set of monopole classes. New results are also obtained concerning boundary cases of the resulting forms of the curvature estimates.
PoPPy is a Point Process toolbox based on PyTorch, which achieves flexible designing and efficient learning of point process models. It can be used for interpretable sequential data modeling and analysis, e.g., Granger causality analysis of multi-variate point processes, point process-based simulation and prediction of…
Optimized method tackles convex optimization with heavy-tailed noise.
SSL theory improves representation learning from raw data.
Robust statistics traditionally focuses on outliers, or perturbations in total variation distance. However, a dataset could be corrupted in many other ways, such as systematic measurement errors and missing covariates. We generalize the robust statistics approach to consider perturbations under any Wasserstein distance…
Proposes a new adversarial model to avoid accuracy vs. adversarial accuracy tradeoff.
Network data appears in very diverse applications, like biological, social, or sensor networks. Clustering of network nodes into categories or communities has thus become a very common task in machine learning and data mining. Network data comes with some information about the network edges. In some cases, this network…
HMQ improves quantization for edge devices with mixed precision.
Improves medication name inference for telemedicine and conversational agents.
Machine learning is being increasingly used by individuals, research institutions, and corporations. This has resulted in the surge of Machine Learning-as-a-Service (MLaaS) - cloud services that provide (a) tools and resources to learn the model, and (b) a user-friendly query interface to access the model. However, suc…
Benchmark tests spoken language models for infant language learning.
SPAT improves adversarial robustness by preserving semantics in adversarial training.
This reviews the econophysics activities in Belgium from my admittedly biased point of view. Unknown historical notes or facts are presented for the first time explaining the aims, whence evolution of the research papers and friendly connections with colleagues. Comments on endeavors are also provided. The lack of offi…
We propose a dynamic edge exchangeable network model that can capture sparse connections observed in real temporal networks, in contrast to existing models which are dense. The model achieved superior link prediction accuracy on multiple data sets when compared to a dynamic variant of the blockmodel, and is able to ext…
We study holomorphic foliations with an affine homogeneous transverse structure. We give a friendly characterization of the case of transversely affine foliations in terms of matrix valued pairs of differential forms. This leads naturally to the study of the case of foliations with singularities. A first extension theo…
More training data can hurt the generalization of adversarially robust models.
These lecture notes are a friendly introduction to monopole Floer homology. We discuss the relevant differential geometry and Morse theory involved in the definition. After developing the relation with the four-dimensional theory, our attention shifts to gradings and correction terms. Finally, we sketch the analogue in…
This paper presents compact notations for concentration inequalities and convenient results to streamline probabilistic analysis. The new expressions describe the typical sizes and tails of random variables, allowing for simple operations without heavy use of inessential constants. They bridge classical asymptotic nota…
Flexible Cox model for time-dependent covariates with complex sparsity patterns.
Paper proposes a new black-box adversarial attack using normalizing flows.
We present a data-driven framework called generative adversarial privacy (GAP). Inspired by recent advancements in generative adversarial networks (GANs), GAP allows the data holder to learn the privatization mechanism directly from the data. Under GAP, finding the optimal privacy mechanism is formulated as a constrain…
Paper tackles robustness in adversarial noise with a meta-optimizer.
Adversarial training achieves optimal test error for shallow networks.