Computer-generated proofs led to a mathematical result.
problem Discovering a mathematical result through computer-generated proofs.
method Combining computer-generated, human-readable proofs with mathematical abstraction.
result Abstracted lemma leading to an interesting mathematical result.
A novel memory mechanism for reinforcement learning agents that stores past events in human-readable language.
problem Lack of interpretability in reinforcement learning agent's memory mechanisms.
method Uses CLIP to associate visual inputs with language tokens, then feeds these tokens to a pretrained language model.
result Significantly faster convergence on challenging continuous recognition tasks.
Benchmark for math reasoning models from human proofs.
problem Measuring and accelerating machine learning models in high-level mathematical reasoning.
method Built a non-synthetic dataset from theorem prover proofs, defined a task for model to fill in missing propositions, used hierarchical transformer to improve performance.
result Neural models can capture non-trivial mathematical reasoning, hierarchical transformer outperforms baseline.
We present the mathematical background of a software package that computes triangulations of mapping tori of surface homeomorphisms, suitable for Jeff Weeks's program SnapPea. It consists of two programs. jmt computes triangulations and prints them in a human-readable format. jsnap converts this format into SnapPea's t…
MiniHack simplifies creation of complex RL environments.
problem Limited availability of challenging RL benchmarks.
method Develops a sandbox framework for easy RL environment design.
result MiniHack enables rapid creation of diverse RL testbeds.
Recently, Reinforcement Learning (RL) approaches have demonstrated advanced performance in image captioning by directly optimizing the metric used for testing. However, this shaped reward introduces learning biases, which reduces the readability of generated text. In addition, the large sample space makes training unst…
Tracr compiles programs into transformer models for interpretability.
problem Uncertainty in understanding transformer model outputs due to unknown learned programs.
method Tracr compiles human-readable programs into known structure transformer models.
result Known structure of Tracr-compiled models serves as ground-truth for interpretability.
Automatically extracts hyperparameter schemas from AI library documentation.
problem Lack of machine-readable hyperparameter schemas for AI automation tools.
method Automatically mines Python docstrings in AI libraries to extract JSON Schemas.
result Effective at extracting machine-readable schemas from 119 AI models.
LLMs can help explain credit risk models but not autonomously.
problem Leveraging LLMs for post-hoc explainability in credit risk models.
method Comparison of LLM outputs with SHAP and coefficient-based attributions on three LMs.
result LLMs reliably preserve feature-importance rankings but poorly align with autonomous explanations.
OutlierTree detects outliers using decision trees and provides explanations.
problem Detecting outliers in data while providing understandable explanations.
method Supervised decision tree splits with 1-d confidence intervals.
result Human-readable explanations for outlier detection.
NFTs with diverse rare attributes sell at higher prices.
problem Understanding how rarity affects NFT market dynamics.
method Analyzed 3.7M NFT transactions across 410 collections.
result Rarer NFTs sell for higher prices and are less risky.
NCVis speeds up data visualization for large datasets.
problem Performance issues in t-SNE for large datasets.
method Noise contrastive estimation for scalable visualization.
result NCVis outperforms state-of-the-art techniques in speed and quality.
Text clustering method replaces centroids with summaries for interpretability and scalability.
problem Efficiently clustering text data while maintaining interpretability and scalability.
method k-NLPmeans and k-LLMmeans, which periodically replace numeric centroids with textual summaries.
result Consistently outperforms classical baselines and recent LLM-based clustering methods.
In this article, we propose the Coopetititve Soft Gating Ensemble or CSGE for general machine learning tasks and interwoven systems. The goal of machine learning is to create models that generalize well for unknown datasets. Often, however, the problems are too complex to be solved with a single model, so several model…
Discover governing equations from data without specifying terms.
problem Discovering differential equations from data without predefined terms.
method Data-driven approach using genetic programming and automatic differentiation.
result Calibrated differential equations from various solutions of a differential equation.
Data analysis in high-dimensional spaces aims at obtaining a synthetic description of a data set, revealing its main structure and its salient features. We here introduce an approach providing this description in the form of a topography of the data, namely a human-readable chart of the probability density from which t…
Proposes a method to reveal nonlinearities in tensor data.
problem Capturing nonlinear relationships in high-dimensional tensor data.
method Linear tensor projection method to maximize prediction accuracy.
result Effective in revealing nonlinear relationships in tensor data.
We present a reinforcement learning framework, called Programmatically Interpretable Reinforcement Learning (PIRL), that is designed to generate interpretable and verifiable agent policies. Unlike the popular Deep Reinforcement Learning (DRL) paradigm, which represents policies by neural networks, PIRL represents polic…
This study improves detection of insider threats using machine learning.
problem Detecting insider threats with anticipation and accuracy.
method Empirically tested 88 machine learning algorithms on CERT dataset, focusing on employee sentiment.
result Random forest algorithms offer the best overall performance, with high accuracy and interpretable rules.
Supervised learning algorithms are nowadays successfully scaling up to datasets that are very large in volume, leveraging the potential of in-memory cluster-computing Big Data frameworks. Still, massive datasets with a number of large-domain categorical features are a difficult challenge for any classifier. Most off-th…
The simulator is an R package that streamlines the process of performing simulations by creating a common infrastructure that can be easily used and reused across projects. Methodological statisticians routinely write simulations to compare their methods to preexisting ones. While developing ideas, there is a temptatio…
SupRB learns rules for continuous decision problems from examples.
problem Learning from continuous choices and explaining decisions to operators.
method SupRB is a supervised rule-based learning system for multi-dimensional continuous problems.
result SupRB provides human-understandable rules for optimal choices and quality predictions.
Paper proposes interpretable RL policies from a mixture of experts.
problem Making RL policies transparent and understandable in real-world applications.
method Policy iteration scheme with interpretable experts and prototypical states.
result Proposed algorithm learns policies comparable to neural networks but more interpretable.
Generative Map learns interpretable neural network maps for camera localization.
problem Creating interpretable maps for neural network-based camera localization.
method Combining generative models with Kalman filters and incorporating additional sensor information.
result Generative Map predicts images closely resembling the true scene and achieves comparable localization performance.
Developed Taylor series for muscle-finger system analysis.
problem Understanding the complex relationship between muscle activity and finger movement.
method Used Dendrite Net to develop Taylor series and construct relation spectrum.
result Found muscle synergy and coupling in hand movement.
Survey of seq2seq models for neural text summarization.
problem Improving fluency and quality of text summaries.
method Comprehensive review of seq2seq models for abstractive text summarization.
result Benchmarking of two models on recent datasets.
We introduce techniques for exploring the functionality of a neural network and extracting simple, human-readable approximations to its performance. By performing gradient ascent on the input space of the network, we are able to produce large populations of artificial events which strongly excite a given classifier. By…
This paper proposes a framework to learn explainable rules from knowledge graphs for better recommendation.
problem Combining side information with explainability in recommendation systems.
method Joint learning framework integrating rule induction from knowledge graphs with a rule-guided neural recommendation model.
result Significant improvements in item recommendation performance over baselines.
Improves transparency of deep neural networks through feature and consistency analysis.
problem Black-box nature of deep learning inference limits transparency for safety-critical systems.
method Structural and linguistic feature analysis, consistency analysis.
result 75% of human workers found input data and results consistent, 70% found inference and results consistent.
STYLE-ANALYZER fixes code style inconsistencies without manual intervention.
problem Manual code reviews are time-consuming and error-prone.
method Unsupervised machine learning with decision tree forest model.
result STYLE-ANALYZER accurately fixes code formatting violations with interpretable rules.
Automatically extracts phenotypes from cancer clinical notes for genetic studies.
problem Lack of structured patient representations in EHRs.
method Clustering of medical terms and sentences in clinical notes.
result 341 significant associations between clinical features and somatic mutations.
BTZSC benchmarks zero-shot text classification across diverse models.
problem Systematically comparing zero-shot text classification across various models.
method Comprehensive benchmark of 22 datasets, comparing NLI cross-encoders, embedding models, rerankers, and instruction-tuned LLMs.
result Rerankers and instruction-tuned LLMs outperform NLI cross-encoders, with rerankers setting a new state-of-the-art.
CFM-BD builds interpretable fuzzy models for Big Data.
problem Maintaining accuracy and interpretability in fuzzy models for Big Data.
method Distributed learning algorithm with three stages: pre-processing, rule induction, and rule selection.
result CFM-BD constructs simpler models with fewer rules and linguistic labels, achieving competitive accuracy.
Project classifies malware using a multi-input LSTM model.
problem Classifying malware with high accuracy and handling class imbalance.
method Supervised multi-class LSTM model trained on annotated malware files.
result Multi-input model using both text and hexadecimal inputs outperformed single formats.
SEP framework teaches LLMs to generate explainable stock predictions.
problem Challenging task of generating human-readable explanations for stock predictions.
method Self-reflective agent and Proximal Policy Optimization (PPO) for autonomous learning.
result Fine-tuned LLM outperforms traditional methods in prediction accuracy and Matthews correlation coefficient.
Several proofs of Fáry--Milnor theorem are presented.
problem Fáry--Milnor theorem
method Sketches several proofs
result Proofs of Fáry--Milnor theorem
Machine learning improves searching for polynomial proofs.
problem Automatically searching for proofs of polynomial inequalities.
method Deep reinforcement learning guiding inference rules in semi-algebraic proof systems.
result Reduces the size of linear programs by several orders of magnitude.
New proof of isoperimetric inequality using Steiner's formula.
problem Proving the isoperimetric inequality in the plane.
method Direct proof using Steiner's formula, bypassing domain existence.
result Establishes the isoperimetric inequality directly.
Machine learning automates proof generation in Coq proof assistant.
problem Automating proof construction in proof assistants.
method Developed ASTactic, a deep learning model generating tactics as ASTs.
result ASTactic can generate effective tactics and prove new theorems.
New proof for Gromov's theorem on almost flat manifolds.
problem Proving Gromov's theorem on almost flat manifolds.
method Inductive proof on dimension.
result New proof for Gromov's theorem.
Corrects a flawed proof of the Kropholler Conjecture.
problem Kropholler Conjecture in relative group theory.
method Explains the flaws and proposes possible ways to correct the proof.
result Provides a clearer understanding of the conjecture's proof difficulties.
Simplified proof of gluing formula for analytic torsion forms.
problem Proving the gluing formula for analytic torsion forms.
method Extending prior work to the family case, presenting a new proof.
result Simplified proof of the gluing formula.
A simplified proof of the Alexander-Conway polynomial exists.
problem Existence of the Alexander-Conway polynomial for links in 3D space.
method Presented an accurate detailed exposition of the proof.
result Existence of the Alexander-Conway polynomial proved.
We give a direct proof that the Freed-Lott differential analytic index is well defined and a condensed proof of the differential Grothendieck-Riemann-Roch theorem. As a byproduct we also obtain a direct proof that the R/Z analytic index is well defined and a condensed proof of the R/Z Grothendieck-Riemann-Roch theorem.
Simplified proof for a theorem about graphs.
problem Proving a generalized Conway--Gordon--Sachs theorem for complete graphs.
method Provided a shorter proof over integers.
result A simpler proof of the generalized theorem.
We offer a simplified proof for Expected Shortfall's dual representation.
problem The dual representation of Expected Shortfall.
method Basic properties of quantile functions.
result New proof of Expected Shortfall's subadditivity.
Proof given for SGD convergence in a concise manner.
problem Convergence of Stochastic Gradient Descent (SGD)
method Self-contained proof
result SGD convergence proven
The Goldman-Parker Conjecture classifies the complex hyperbolic C-reflection ideal triangle groups up to discreteness. We proved the Goldman-Parker Conjecture in [Ann. of Math. 153 (2001) 533--598] using a rigorous computer-assisted proof. In this paper we give a new and improved proof of the Goldman-Parker Conjecture.…