arXiv research

Paper interprets ResNets via gate-network controls and deep-layer classifications.

We propose to use boosted regression trees as a way to compute human-interpretable solutions to reinforcement learning problems. Boosting combines several regression trees to improve their accuracy without significantly reducing their inherent interpretability. Prior work has focused independently on reinforcement lear…

In recent years, deep learning researchers have focused on how to find the interpretability behind deep learning models. However, today cognitive competence of human has not completely covered the deep learning model. In other words, there is a gap between the deep learning model and the cognitive mode. How to evaluate…

Meta-learning approach to learn interpretable models from human feedback.

We proved that the solutions of $C^2$ class of certain ODEs or PDEs belong to a class of harmonic maps between two convenient generalized Lagrange spaces.

Adaptive Bayesian learning agent for non-stationary bandits.

MaxVol NMF maximizes the volume of $H$ in NMF for better sparse and interpretable solutions.

Simpler model outperforms deep learning for disease prediction.

More and more AI services are provided through APIs on cloud where predictive models are hidden behind APIs. To build trust with users and reduce potential application risk, it is important to interpret how such predictive models hidden behind APIs make their decisions. The biggest challenge of interpreting such predic…

Study first BGG operators on homogeneous geometries.

We present an explicit example of a fast decaying solution to the modified Novikov--Veselov equation with a one-point singularity in the space-time. It is constructed by using the geometrical interpretation of the Moutard transformation of solutions to this equation and the Enneper minimal surface.

Interpretable framework evaluates structure learning methods for causal discovery from observational data.

Model-agnostic interpretation methods can mislead if not used carefully.

Recent results using inverse scattering techniques interpret every solution $φ(x,y)$ of the sine-Gordon equation as a non-linear superposition of solutions along the axes $x=0$ and $y=0$. Here we provide a geometric method of integration, as well as a geometric interpretation. Specifically, every weakly regular surface…

A new principle minimizes residual and introduces momentum to improve PDE solution dynamics.

In recent years, machine learning researchers have focused on methods to construct flexible and interpretable prediction models. However, an interpretability evaluation, a relationship between generalization performance and an interpretability of the model and a method for improving the interpretability have to be cons…

This paper presents an automated approach for interpretable feature recommendation for solving signal data analytics problems. The method has been tested by performing experiments on datasets in the domain of prognostics where interpretation of features is considered very important. The proposed approach is based on Wi…

New geometric insights reveal properties of adversarial training problems.

A construction of blowing up solutions to the modified Novikov-Veselov equation is proposed. It is based on the Moutard transformation of two-dimensional Dirac operators and its geometrical interpretation via surface geometry. An explicit example of such a solution constructed by using the Enneper minimal surface is di…

Interpretability of ML models improves healthcare decisions.

As the use of black-box models becomes ubiquitous in high stake decision-making systems, demands for fair and interpretable models are increasing. While it has been shown that interpretable models can be as accurate as black-box models in several critical domains, existing fair classification techniques that are interp…

Using a supergeometric interpretation of field functionals, we show that for a class of classical field models used for realistic quantum field theoretic models, an infinite-dimensional supermanifold (smf) of classical solutions in Minkowski space can be constructed. That is, we show that the smf of smooth Cauchy data …

This paper makes kernels interpretable for wide feature matrices.

Automated fatigue assessment using ECG and actigraphy sensors.

The paper studies how neural policies can be interpreted using decision trees.

Recently, Mahoney and Orecchia demonstrated that popular diffusion-based procedures to compute a quick \emph{approximation} to the first nontrivial eigenvector of a data graph Laplacian \emph{exactly} solve certain regularized Semi-Definite Programs (SDPs). In this paper, we extend that result by providing a statistica…

Paper proposes an efficient method to optimize neural networks without backpropagation.

The paper investigates instance-based interpretation methods for VAEs.

IMPACC improves consensus clustering for bioinformatics data.

Selective neural network improves credit risk prediction while maintaining interpretability.

Algorithm identifies intended fairness constraints from expert demonstrations for fair clustering.

Differential equations are derived for a continuous limit of iterated Schwarzian reflection of analytic curves, and solutions are interpreted as geodesics in an infinite-dimensional symmetric space geometry.

It is commonly believed that increasing the interpretability of a machine learning model may decrease its predictive power. However, inspecting input-output relationships of those models using visual analytics, while treating them as black-box, can help to understand the reasoning behind outcomes without sacrificing pr…

New priors improve robustness and interpretability in penalized regression.

The paper formalizes feature attribution to address inconsistent definitions and evaluate methods.

We introduce the localized Lasso, which is suited for learning models that are both interpretable and have a high predictive power in problems with high dimensionality $d$ and small sample size $n$. More specifically, we consider a function defined by local sparse models, one at each data point. We introduce sample-wis…

E-LDA offers faster, interpretable LDA topic models.

Framework for interpreting ML models to reveal properties of real-world phenomena.

An important feature of successful supervised machine learning applications is to be able to explain the predictions given by the regression or classification model being used. However, most state-of-the-art models that have good predictive power lead to predictions that are hard to interpret. Thus, several model-agnos…

We study the problem of subspace tracking in the presence of missing data (ST-miss). In recent work, we studied a related problem called robust ST. In this work, we show that a simple modification of our robust ST solution also provably solves ST-miss and robust ST-miss. To our knowledge, our result is the first `compl…

New approach interprets Nyström for kernel machines with geometric insight.

In this paper we continue investigation of the constant astigmatism equation z_{yy} + (1/z)_{xx} + 2 = 0. We newly interpret its solutions as describing spherical orthogonal equiareal patterns, with relevance to two-dimensional plasticity. We show how the classical Bianchi superposition principle for the sine-Gordon eq…

Transforms solutions of Davey-Stewartson II equation geometrically.

We revisit the task of learning a Euclidean metric from data. We approach this problem from first principles and formulate it as a surprisingly simple optimization problem. Indeed, our formulation even admits a closed form solution. This solution possesses several very attractive properties: (i) an innate geometric app…

There has been growing recent interest in probabilistic interpretations of kernel-based methods as well as learning in Banach spaces. The absence of a useful Lebesgue measure on an infinite-dimensional reproducing kernel Hilbert space is a serious obstacle for such stochastic models. We propose an estimation model for …

New deep learning model interprets tabular data with variable selection and explainability.

SG-PALM learns interpretable tensor models for high-dimensional data.

This work addresses the situation where a black-box model with good predictive performance is chosen over its interpretable competitors, and we show interpretability is still achievable in this case. Our solution is to find an interpretable substitute on a subset of data where the black-box model is overkill or nearly …