Bayesian symbolic regression automates model discovery from data.
problem Learning closed-form mathematical models from data using heuristic methods.
method Probabilistic approach to symbolic regression, connecting to information theory and statistical physics.
result Probabilistic approach provides model plausibility and performance guarantees.
Robust subgroup discovery finds non-redundant, statistically significant subgroups.
problem Finding interpretable, robust subgroups from data.
method Formulated subgroup lists for univariate and multivariate targets, used MDL principle and greedy heuristic SSD++.
result SSD++ outperforms previous methods in quality and size of subgroup lists.
CD-RCA method identifies causal relationships in prediction errors without predefined graphs.
problem Challenges in diagnosing prediction errors due to lack of transparency in black-box models.
method Causal-Discovery-based Root-Cause Analysis (CD-RCA) method that estimates causal relationships without predefined causal graphs.
result CD-RCA outperforms heuristic attribution methods in identifying variable contributions to prediction errors.
Proposes a new method for finding non-redundant, standout subgroups in numeric datasets.
problem Mining large numbers of redundant subgroups in numeric datasets.
method Dispersion-aware problem formulation based on MDL principle for subgroup set discovery.
result Empirically demonstrates SSD++ returns outstanding subgroup lists.
Clustering algorithms have regained momentum with recent popularity of data mining and knowledge discovery approaches. To obtain good clustering in reasonable amount of time, various meta-heuristic approaches and their hybridization, sometimes with K-Means technique, have been employed. A Kalman Filtering based heurist…
The paper discovers and evaluates support and resistance levels in financial time series.
problem Understanding and predicting support and resistance levels in financial markets.
method Developed a heuristic discovery algorithm to identify SR levels in intraday price series.
result Discovered SR levels statistically significantly reverse price trends and have a decay aspect over time.
A new geometrically-motivated algorithm for nonnegative matrix factorization is developed and applied to the discovery of latent "topics" for text and image "document" corpora. The algorithm is based on robustly finding and clustering extreme points of empirical cross-document word-frequencies that correspond to novel …
New method detects latent common causes from observational data.
problem Detecting latent common causes in observational data.
method Modified causal discovery algorithms to detect latent common causes.
result Successfully detects latent common causes in various noise regimes and real data.
Extends knockoff filter for composite null hypotheses in variable selection.
problem Handling composite null hypotheses in variable selection.
method Developed two methods for composite inference with knockoffs: S-OLS and FRPP.
result Proposed heuristic variants of S-OLS outperforming BH procedure for composite nulls.
System discovers new classes from unlabeled data, improving model performance.
problem Handling datapoints outside initial training distribution.
method Develops new classes through semi-supervised learning, using Dataset Reconstruction Accuracy and class learnability.
result Demonstrates improved model quality through automatic class discovery.
Optimal algorithm selects biological models without prior info.
problem Determining the correct biological model without prior knowledge.
method Systems biology models and likelihood-free inference.
result Improved model selection performance over conventional methods.
New method controls false discoveries in structured hypothesis spaces.
problem Controlling false discoveries in large-scale, interconnected hypothesis spaces.
method Reproducing Kernel Hilbert Space (RKHS) optimization for structured FDR control.
result Unified framework for continuous domains, graphs, and hierarchies.
New models suggest molecules that are often unfeasible to synthesize.
problem Models suggest molecules that are difficult to synthesize.
method Used a computer-aided synthesis planning program to analyze synthesizability of molecules generated by state-of-the-art models.
result State-of-the-art models generate molecules that are often unfeasible to synthesize.
ALIAS uses RL to learn DAGs without acyclicity constraints.
problem Efficiently learning DAGs from observational data without acyclicity constraints.
method ALIAS employs RL to generate DAGs in a single step with optimal complexity, bypassing acyclicity constraints.
result ALIAS outperforms state-of-the-art methods in causal discovery.
Python package 'nonconform' simplifies conformal anomaly detection.
problem Heuristic thresholding in anomaly detection systems.
method 'nonconform' package converts anomaly scores into calibrated p-values.
result Statistically principled anomaly detection is made accessible.
Boolean matrix factorization (BMF) is a popular and powerful technique for inferring knowledge from data. The mining result is the Boolean product of two matrices, approximating the input dataset. The Boolean product is a disjunction of rank-1 binary matrices, each describing a feature-relation, called pattern, for a g…
Automates kernel discovery for longitudinal data analysis.
problem Handling irregularly sampled, sparse longitudinal data with multilevel correlation.
method Combines deep neural networks and non-parametric kernel methods to discover complex multilevel correlation structure.
result Significantly outperforms state-of-the-art methods on benchmark data sets.
The TREX is a recently introduced method for performing sparse high-dimensional regression. Despite its statistical promise as an alternative to the lasso, square-root lasso, and scaled lasso, the TREX is computationally challenging in that it requires solving a non-convex optimization problem. This paper shows a remar…
FinCARE combines financial data and AI reasoning to improve causal analysis of financial performance.
problem Correlation-based analysis fails to capture true causal relationships in financial performance.
method Hybrid framework integrating causal discovery algorithms with financial domain knowledge from SEC filings and LLM reasoning.
result KG+LLM-enhanced methods improve causal discovery across PC, GES, and NOTEARS by 36-366%.
In many scientific tasks we are interested in discovering whether there exist any correlations in our data. This raises many questions, such as how to reliably and interpretably measure correlation between a multivariate set of attributes, how to do so without having to make assumptions on distribution of the data or t…
Causal discovery predicts unobserved joint statistics from observed data.
problem Inferring properties of unobserved joint distributions from observed data.
method Infer causal models from observed data to predict statistical properties of unobserved sets.
result Sparse causal graphs can be more useful than dense ones in predicting unobserved joint distributions.
Learning a Bayesian network structure from data is an NP-hard problem and thus exact algorithms are feasible only for small data sets. Therefore, network structures for larger networks are usually learned with various heuristics. Another approach to scaling up the structure learning is local learning. In local learning…
Bayesian optimization offers the possibility of optimizing black-box operations not accessible through traditional techniques. The success of Bayesian optimization methods such as Expected Improvement (EI) are significantly affected by the degree of trade-off between exploration and exploitation. Too much exploration c…
SkewD robustly discovers causal relationships in skewed noise models.
problem Distinguishing cause from effect in skewed noise models.
method SkewD extends normal-distribution framework to skew-normal setting for reliable inference.
result SkewD remains robust under high skewness, improving reliability.
Bin2vec learns executable program representations for security tasks.
problem Manual rule and heuristic definition for binary program analysis is tedious and time-consuming.
method Bin2vec uses Graph Convolutional Networks (GCN) on computational program graphs.
result Improvement over state-of-the-art methods for binary analysis tasks.
In this report paper we first present a report of the Advanced Machine Learning Course Project on the provided data set and then present a novel heuristic algorithm for exact Bayesian network (BN) structure discovery that uses decomposable scoring functions. Our algorithm follows a different approach to solve the probl…
We consider the maximum likelihood estimation of sparse inverse covariance matrices. We demonstrate that current heuristic approaches primarily encourage robustness, instead of the desired sparsity. We give a novel approach that solves the cardinality constrained likelihood problem to certifiable optimality. The approa…
Discovering causal structure among a set of variables is a fundamental problem in many empirical sciences. Traditional score-based casual discovery methods rely on various local heuristics to search for a Directed Acyclic Graph (DAG) according to a predefined score function. While these methods, e.g., greedy equivalenc…
Paper proposes a new Bayesian optimisation method to handle aleatoric uncertainty.
problem Representing and minimizing aleatoric noise in Bayesian optimisation.
method Heteroscedastic Gaussian process (GP) surrogate model with AEI and ANPEI acquisition functions.
result Improved performance on toy problems and real-world datasets compared to homoscedastic methods.
The discovery of clinical biomarkers requires large patient cohorts and is aided by a pooled data approach across institutions. In many countries, data protection constraints, especially in the clinical environment, forbid the exchange of individual-level data between different research institutes, impeding the conduct…
New test assesses reliability of auto-generated features.
problem Lack of reliable assessment for auto-generated features.
method Selective inference framework for statistical testing.
result Proposes a statistical test for auto-generated features in linear models.
Proposes a new method for subgroup analysis using optimal trees with parameter fusion.
problem Challenges of greedy heuristics and overfitting in tree-based recursive partitioning methods.
method Fused optimal causal tree method leveraging mixed integer optimization (MIO) for globally optimal partitions and parameter fusion.
result Substantial improvement in subgroup discovery accuracy and statistical efficiency.
XGES improves GES by favoring early edge deletion, outperforming GES in finite data settings.
problem Learning directed acyclic graphs from finite data.
method Extremely Greedy Equivalent Search (XGES) improves GES by favoring early edge deletion.
result XGES consistently outperforms GES in recovering the correct graphs, and is 10 times faster.
AI-Interpret transforms opaque policies into simple, interpretable decision rules.
problem Designing effective decision aids for professionals to mitigate decision-making biases.
method Combining imitation learning, program induction, and clustering to transform learned policies into interpretable descriptions.
result Providing interpretable decision rules as flowcharts significantly improves people's planning strategies and decisions.
Depth is a key component of Deep Neural Networks (DNNs), however, designing depth is heuristic and requires many human efforts. We propose AutoGrow to automate depth discovery in DNNs: starting from a shallow seed architecture, AutoGrow grows new layers if the growth improves the accuracy; otherwise, stops growing and …
A popular tool for unsupervised modelling and mining multi-aspect data is tensor decomposition. In an exploratory setting, where and no labels or ground truth are available how can we automatically decide how many components to extract? How can we assess the quality of our results, so that a domain expert can factor th…
Rejoinder on slope heuristics for model selection in regression.
problem Model selection in least-squares fixed-design regression with biased models and general noise.
method Proves the slope heuristics works even with significant bias and computes expectations for Gaussian noise.
result The slope heuristics is valid even when models are biased and noise has a general dependence structure.
Proposes a method to imitate active learning heuristics for better performance.
problem The performance of active learning heuristics depends on the classifier model and data structure.
method Imitates the selection of the best active learning heuristic using DAGGER.
result Outperforms state-of-the-art imitation learners and heuristics on well-known datasets.
Motivated by concerns that machine learning algorithms may introduce significant bias in classification models, developing fair classifiers has become an important problem in machine learning research. One important paradigm towards this has been providing algorithms for adversarially learning fair classifiers (Zhang e…
This research evaluates and introduces new heuristics for clustering Bitcoin blockchain entities.
problem Efficiently analyzing the vast number of Bitcoin blockchain entities.
method Examined and introduced four new heuristics for clustering Bitcoin blockchain entities.
result Introduced clustering ratio to measure heuristic effectiveness.
Novel RL approach for molecular design using quantum mechanics.
problem Existing RL methods for molecular design are limited in scope and reward function.
method Formulation in Cartesian coordinates, direct use of quantum mechanics for reward function, translation and rotation invariant state-action space.
result Agent efficiently learns to solve molecular design tasks from scratch.
Link prediction is a key problem for network-structured data. Link prediction heuristics use some score functions, such as common neighbors and Katz index, to measure the likelihood of links. They have obtained wide practical uses due to their simplicity, interpretability, and for some of them, scalability. However, ev…
Nemo improves WS learning pipeline by 20%.
problem Creating effective labeling heuristics for weak supervision.
method Interactive procedure for designing heuristics, strategic data selection, contextualization of heuristics.
result Improves WS learning pipeline by 20%.
This paper evaluates heuristics and hyperparameters in weight-sharing NAS methods.
problem Improving the performance of weight-sharing NAS methods.
method Systematic evaluation of heuristics and hyperparameters in weight-sharing NAS algorithms.
result Some heuristics negatively impact super-net and stand-alone performance correlation.
Interactive weak supervision learns useful heuristics from user feedback.
problem Creating useful heuristics for large labeled datasets is tedious and subjective.
method Develops an interactive framework for learning heuristics from user feedback.
result Only a few feedback iterations are needed to train models without ground truth labels.
We propose a general approach to modeling semi-supervised learning (SSL) algorithms. Specifically, we present a declarative language for modeling both traditional supervised classification tasks and many SSL heuristics, including both well-known heuristics such as co-training and novel domain-specific heuristics. In ad…
Differentiable causal discovery methods perform robustly under model violations.
problem Causal discovery algorithms struggle with real-world data due to unverifiable causal assumptions.
method Benchmarked differentiable causal discovery methods under eight model assumption violations.
result Differentiable causal discovery methods exhibit robust performance under Structural Hamming Distance and Structural Intervention Distance metrics.
New framework uses background knowledge to speed up causal discovery.
problem Scalable causal discovery for large datasets.
method Utilizes background knowledge during causal discovery process.
result Background knowledge reduces computational requirements and improves structure quality.