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.
Bayesian active learning improves holistic educational assessments.
HEAR benchmark evaluates audio representations for diverse tasks.
Holistic GLMs add constraints for better model quality.
Paper assesses holistic risks of inference attacks on ML models.
Framework audits synthetic datasets for trustworthiness across various use cases.
Unsupervised domain adaptation methods aim to alleviate performance degradation caused by domain-shift by learning domain-invariant representations. Existing deep domain adaptation methods focus on holistic feature alignment by matching source and target holistic feature distributions, without considering local feature…
New holistic approach measures sample-level adversarial vulnerability for trustworthy systems.
Risk is part of the fabric of every business; surprisingly, there is little work on establishing best practices for systematic, repeatable risk identification, arguably the first step of any risk management process. In this paper, we present a proposal that constitutes a more holistic risk management approach, a method…
We propose a new scalable algorithm for holistic linear regression building on Bertsimas & King (2016). Specifically, we develop new theory to model significance and multicollinearity as lazy constraints rather than checking the conditions iteratively. The resulting algorithm scales with the number of samples in th…
The paper introduces ESE scores for farmers to assess climate change risks.
This paper proposes a new approach to RL by focusing on the value-improvement path.
MARS-Gym framework for marketplaces to train and evaluate recommender systems.
Generic generation and manipulation of text is challenging and has limited success compared to recent deep generative modeling in visual domain. This paper aims at generating plausible natural language sentences, whose attributes are dynamically controlled by learning disentangled latent representations with designated…
P3I learns holistic scene representations from a single image.
Paper proposes a holistic optimization for civil structures considering uncertainties.
This paper presents the first use of graph neural networks (GNNs) for higher-order proof search and demonstrates that GNNs can improve upon state-of-the-art results in this domain. Interactive, higher-order theorem provers allow for the formalization of most mathematical theories and have been shown to pose a significa…
Recently, deep neural networks have demonstrated excellent performances in recognizing the age and gender on human face images. However, these models were applied in a black-box manner with no information provided about which facial features are actually used for prediction and how these features depend on image prepro…
Optimizes fund portfolio updates using linear programming and heuristic search.
Paper tackles leverage effect estimation from noisy data.
Holistic Filter Pruning reduces DNN complexity efficiently.
FinReflectKG - EvalBench benchmarks financial KG extraction from SEC 10-K filings.
In likelihood-free settings where likelihood evaluations are intractable, approximate Bayesian computation (ABC) addresses the formidable inference task to discover plausible parameters of simulation programs that explain the observations. However, they demand large quantities of simulation calls. Critically, hyperpara…
The current Deep Learning (DL) landscape is fast-paced and is rife with non-uniform models, hardware/software (HW/SW) stacks, but lacks a DL benchmarking platform to facilitate evaluation and comparison of DL innovations, be it models, frameworks, libraries, or hardware. Due to the lack of a benchmarking platform, the …
B-cos transformers explain Vision Transformers' decisions.
FinReflectKG builds a comprehensive financial knowledge graph from SEC filings, improving extraction quality.
This study optimizes quantized neural networks by considering model architecture and quantization types.
New approach to fairness in machine learning models using conformal prediction.
We investigate the forecasting ability of the most commonly used benchmarks in financial economics. We approach the usual caveats of probabilistic forecasts studies -small samples, limited models and non-holistic validations- by performing a comprehensive comparison of 15 predictive schemes during a time period of over…
Translating renderings (e. g. PDFs, scans) into hierarchical document structures is extensively demanded in the daily routines of many real-world applications. However, a holistic, principled approach to inferring the complete hierarchical structure of documents is missing. As a remedy, we developed "DocParser": an end…
Designs a robust data-driven decision-making model to handle multiple overfitting sources.
The paper proposes a method to calibrate healthcare AI models for reliability and interpretability.
We give a short, simple and conceptual proof, based on spin structures, of sphere eversion: an embedded 2-sphere in can be turned inside out by regular homotopy. Ingredients of this eversion are seamlessly connected. We also give the mathematical origins of the proof: the Hopf fibration, and the topological struc…
Data extracted from software repositories is used intensively in Software Engineering research, for example, to predict defects in source code. In our research in this area, with data from open source projects as well as an industrial partner, we noticed several shortcomings of conventional data mining approaches for c…
Proposes a method for ranking items across multiple aspects based on user feedback.
Article evaluates AI security threats and proposes multiple measures.
New method adapts to user preferences dynamically, improving recommendation models.
We discuss recently emerging applications of the state-of-art deep learning methods on optical microscopy and microscopic image reconstruction, which enable new transformations among different modes and modalities of microscopic imaging, driven entirely by image data. We believe that deep learning will fundamentally ch…
Recent advances in visual tracking are based on siamese feature extractors and template matching. For this category of trackers, latest research focuses on better feature embeddings and similarity measures. In this work, we focus on building holistic object representations for tracking. We propose a framework that is d…
Proposes training neural networks to predict uncertainty for out-of-distribution inputs.
We present a framework based on neural networks to extract music scores directly from polyphonic audio in an end-to-end fashion. Most previous Automatic Music Transcription (AMT) methods seek a piano-roll representation of the pitches, that can be further transformed into a score by incorporating tempo estimation, beat…
We present a new machine learning and text information extraction approach to detection of cyber threat events in Twitter that are novel (previously non-extant) and developing (marked by significance with respect to similarity with a previously detected event). While some existing approaches to event detection measure …
A model integrates CNN and LSTM with LLM for better stock forecasting.
This work shifts focus from prediction to intervention in social systems.
PaRCE estimates model confidence for CNNs across various uncertainties.
This paper provides a holistic study of how stock prices vary in their response to financial disclosures across different topics. Thereby, we specifically shed light into the extensive amount of filings for which no a priori categorization of their content exists. For this purpose, we utilize an approach from data mini…
EQ-Net combines LLR estimation and quantization using deep learning.
FinMaster benchmarks LLMs in financial tasks, revealing gaps in reasoning.
We take the holistic approach of computing an OTC claim value that incorporates credit and funding liquidity risks and their interplays, instead of forcing individual price adjustments: CVA, DVA, FVA, KVA. The resulting nonlinear mathematical problem features semilinear PDEs and FBSDEs. We show that for the benchmark v…