Research
On-device research index

arXiv research

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.

168,695 papers · 148 categories

Trend · papers per month

1122 · Mar 202319922001200920172026
25 results for CBM

PCBM improves neural network generalization by partially observing concepts.

problem Decreased generalization performance due to observing all concepts in CBM.
method Developed a theoretical analysis of PCBM's Bayesian generalization error.
result PCBM's generalization error is lower than CBM's due to partial concept observation.

This paper introduces the combinatorial Boolean model (CBM), which is defined as the class of linear combinations of conjunctions of Boolean attributes. This paper addresses the issue of learning CBM from labeled data. CBM is of high knowledge interpretability but naïve learning of it requires exponentially large compu…

2017-11-07abs ↗pdf ↗

Study clarifies Bayesian generalization error in CBM for 3-layered linear neural networks.

problem Understanding the generalization error in concept bottleneck models.
method Mathematical analysis of Bayesian generalization error and free energy in CBM for 3-layered linear neural networks.
result CBM significantly alters the parameter region and Bayesian generalization error compared to standard models.

PCBMs turn any neural network into interpretable models without dense annotations.

problem Restrictive nature of CBMs and lack of dense concept annotations in training data.
method Introduce PCBMs that can turn any neural network into interpretable models without dense annotations.
result PCBMs can turn any neural network into interpretable models without dense annotations, improving interpretability and performance.

HCBM improves deep learning explainability by non-linear concept aggregation.

problem Lack of explainable and accurate predictions in deep learning for high-stake decisions.
method Introduce Hoeffding Concept Bottleneck Models (HCBM) using Hoeffding functional decomposition of gradient-boosted trees for non-linear and sparse concept aggregation.
result HCBM outperforms standard linear CBM and is robust to interconcept leakage.

CREAM models enable concept-grounded predictions and interpretability.

problem Designing models that can encode and extend prior knowledge about concept-concept and concept-task relationships.
method Proposes a flexible and efficient framework (CREAMs) that encodes arbitrary CCC-C and CoYC o Y relationships, incorporating a side-channel for incomplete concept sets.
result CREAM models achieve competitive task performance while encouraging concept-grounded predictions, avoiding concept leakage and achieving black-box-level performance.

These are lecture notes on scale calculus and M-polyfolds written for a graduate course at UNICAMP March-June 2018 and an advanced mini-course given during the biannual meeting of Brazilian mathematicians, CBM-32, at IMPA in August 2019.

2019-08-04abs ↗pdf ↗

Framework learns interpretable concepts from data without interventions.

problem Learning spurious correlations between concepts in CBMs.
method Causal representation learning (CRL) to align latent variables with interpretable concepts using few labels.
result Framework provides theoretical guarantees on correctness and number of required labels without interventions.

Method reconstructs neuron models from spike times efficiently.

problem Reconstructing neuron models from spike times in degenerate populations.
method Combining deep learning with DICs to map spike times to DIC densities and generate degenerate CBM populations.
result Fast and scalable reconstruction of degenerate populations from spike recordings.

This work improves interpretability in deep learning models by introducing a two-level concept discovery framework.

problem High complexity and lack of interpretability in deep learning models, especially for safety-critical tasks.
method Concept Bottleneck Models (CBMs) framework combining vision-language models and data-driven coarse-to-fine concept selection.
result The proposed framework outperforms recent CBM approaches and provides a principled interpretability.

BC-LLM uses LLMs to find concepts without predefined sets, improving interpretability and performance.

problem Finding a balance between interpretability and accuracy in concept extraction models.
method Bayesian approach with LLMs as both concept extractor and prior.
result BC-LLM outperforms interpretable and black-box models across various datasets.

ECBMs unify concept-based interpretations in deep learning models.

problem Suboptimal final accuracy and lack of concept interaction and conditional dependencies.
method ECBMs use a set of neural networks to define joint energy, enabling concept correction and conditional dependency quantification.
result ECBMs achieve higher accuracy and richer concept interpretations compared to state-of-the-art methods.

A 2008 general overview on Weil-Petersson geometry is offered. A preliminary plan for the subsequent CBMS lectures at Central Connecticut State University is included. Mirzakhani's solution of Witten-Kontsevich is not included - this work essentially requires its own lectures. Lectures on Mirzakhani's Witten-Kontsevich…

2012-02-18abs ↗pdf ↗

Proposes ConRad model for lung cancer classification using radiomics and interpretable machine learning.

problem Lack of interpretability in deep neural networks for cancer diagnosis.
method Integration of radiomics and DNN-predicted biomarkers in interpretable classifiers (ConRad).
result ConRad models outperform CNNs in five-fold cross-validation.

Extends V-IP framework to use LLMs for generating task-relevant concepts, improving interpretability and performance.

problem Limited applicability of V-IP to small-scale tasks due to manual data annotation.
method Integrates Foundational Models with Large Language and Multimodal Models to generate and annotate concepts.
result FM+V-IP achieves better test performance with fewer concepts/queries compared to other frameworks.

Concept-driven OPE reduces variance in off-policy decision evaluation.

problem High variance in off-policy decision evaluation due to limited sample sizes.
method Integrating human-explainable concepts into OPE to reduce variance.
result Concept-based OPE estimators remain unbiased and reduce variance when concepts are known and predefined.