Paper applies ANOVA decomposition for interpretable data approximation.
problem High-dimensional data interpretation and dimensionality reduction.
method ANOVA decomposition and Grouped Transformations for interpretability.
result Ability to rank variable interactions and unimportant variables.
GMT improves interpretability of XGNNs by approximating SubMT.
problem Limited understanding of existing interpretable subgraph learning methods.
method Formulated subgraph multilinear extension (SubMT) and designed GMT architecture.
result GMT outperforms state-of-the-art in both interpretability and generalizability.
Closed-form polynomial approximations replace MLPs in transformers, enabling new interpretability methods.
problem Replacing MLPs with polynomial approximations for transformer models.
method Theoretical derivation of closed-form least-squares approximations of MLPs and GLUs using polynomial functions.
result Polynomial approximations explain over 95% of MLP and GLU outputs' variance, enabling interpretability.
A theory for approximating complex concepts with simple decision trees.
problem Approximating complex concepts with simple decision trees.
method Introducing interpretable approximations, studying binary concept approximation by decision trees.
result A trichotomy of cases for approximating a binary concept by decision trees based on a simple class.
Tree ensembles, such as random forest and boosted trees, are renowned for their high prediction performance, whereas their interpretability is critically limited. In this paper, we propose a post processing method that improves the model interpretability of tree ensembles. After learning a complex tree ensembles in a s…
Paper interprets ResNets via gate-network controls and deep-layer classifications.
problem Understanding the performance mechanism of ResNets.
method Constructs typical solutions using gate-network controls and deep-layer classifications.
result Proves the universal-approximation capability of ResNets.
The ability to interpret machine learning models has become increasingly important now that machine learning is used to inform consequential decisions. We propose an approach called model extraction for interpreting complex, blackbox models. Our approach approximates the complex model using a much more interpretable mo…
The problem of explaining deep learning models, and model predictions generally, has attracted intensive interest recently. Many successful approaches forgo global approximations in order to provide more faithful local interpretations of the model's behavior. LIME develops multiple interpretable models, each approximat…
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…
This work tackles sparse coding in DLRA for interpretable multiway data.
problem Sparse coding in DLRA for interpretable multiway data.
method Proposes a new sparse-coding subproblem (MSC) and several algorithms to solve it.
result DLRA extends low-rank approximations, reducing variance and enhancing interpretability.
LI-ITR combines flexible ML with interpretable approximations for personalized treatment rules.
problem Combining flexibility and interpretability in personalized treatment rules.
method Uses variational autoencoders and a mixture of interpretable experts.
result Accurately recovers true local coefficients and optimal treatment strategies.
Unified framework interprets SSL models, revealing biases.
problem Interpreting black-box SSL models for transparency.
method KREPES framework using Representer Landmarks and Nyström approximation.
result Direct audit of SSL latent space without supervision.
Study topological quantum mechanics on orbifolds with geometric interpretation.
problem Quantum mechanical models on symplectic orbifolds.
method Explicit orbifold version of quantum HKR map and exact semi-classical approximation.
result Geometric and quantum field theoretic interpretation of orbifold algebraic index.
DeepSKA provides interpretable, reliable neural approximations for SRNs.
problem Estimating expected outputs in SRNs is computationally challenging and unreliable.
method Jointly achieves interpretability, reliability, and computational gains with DeepSKA.
result Delivers accurate predictions and substantial efficiency improvements across SRNs.
We propose a novel Shapley value approach to help address neural networks' interpretability and "vanishing gradient" problems. Our method is based on an accurate analytical approximation to the Shapley value of a neuron with ReLU activation. This analytical approximation admits a linear propagation of relevance across …
New architectures improve KANs, making them more interpretable and accurate.
problem Improving Kolmogorov-Arnold networks while maintaining interpretability.
method Overprovisioned architectures combined with sparsification, deep supervision, and depth selection, optimized with a minimum description length objective.
result Combining sparsification with depth selection achieves competitive or superior accuracy while discovering smaller models.
The paper argues for interpreting neural networks as approximating the true posterior, enhancing in-context learning.
problem The limitations of traditional MLE interpretation in large-scale, single-epoch training setups.
method Demonstrates the power of interpreting neural networks as approximations of the true posterior, using experiments to predict generalizations.
result Models become robust in-context learners by effectively composing knowledge from their training data, revealing surprising generalizations.
The paper proposes an interpretable off-policy learning algorithm for medical treatments.
problem Lack of interpretable methods for personalized treatment decisions from observational data.
method Hyperbox search approach for interpretable policies in disjunctive normal form.
result The proposed algorithm outperforms state-of-the-art methods in terms of regret and is rated highly interpretable by clinical experts.
The paper connects machine learning interpretability with learning theory.
problem Performance and explanation generalization in local machine learning models.
method Theoretical analysis and empirical validation of local approximation explanations.
result Theoretical bounds on test-time accuracy and explanation generalization.
We show that a neural network with arbitrary depth and non-linearities, with dropout applied before every weight layer, is mathematically equivalent to an approximation to a well known Bayesian model. This interpretation might offer an explanation to some of dropout's key properties, such as its robustness to over-fitt…
The paper interprets diffusion models as gradient descent and proposes a new sampler.
problem Improving the efficiency and quality of diffusion models.
method Interprets diffusion models as gradient descent and proposes a new sampler.
result The new sampler achieves state-of-the-art FID scores and generates high quality samples.
A hybrid model combines piecewise linear and neural components for interpretable predictions.
problem Post-hoc interpretable methods lead to contradictory explanations and lower prediction accuracy.
method Hybrid model with piecewise linear and neural components.
result The model achieves good interpretability and state-of-the-art accuracy.
Brain decoding is a popular multivariate approach for hypothesis testing in neuroimaging. It is well known that the brain maps derived from weights of linear classifiers are hard to interpret because of high correlations between predictors, low signal to noise ratios, and the high dimensionality of neuroimaging data. T…
L-C2ST improves local diagnostics for SBI approximations.
problem Evaluating trustworthiness of posterior approximations in SBI.
method Local evaluation of posterior estimators at any observation.
result Offers better statistical power and interpretability.
FCM efficiently approximates committor function with interpretable kernel model.
problem Approximating committor function in stochastic systems.
method Kernel-based approach using randomized linear algebra.
result FCM outperforms neural networks in accuracy and training speed.
A new method improves adversarial robustness and interpretability with reduced training time.
problem Adversarial attacks on deep neural networks.
method A novel regularizer incorporating first and second order information via a quadratic approximation to the adversarial loss.
result Single iteration of the proposed regularizer achieves stronger robustness than prior methods.
Deep Gaussian Processes (DGPs) combine the expressiveness of Deep Neural Networks (DNNs) with quantified uncertainty of Gaussian Processes (GPs). Expressive power and intractable inference both result from the non-Gaussian distribution over composition functions. We propose interpretable DGP based on approximating DGP …
New approach interprets Nyström for kernel machines with geometric insight.
problem No comparative study over Nyström-based kernel machine approaches.
method Developed a new approach with geometric interpretation, showing equivalence to existing methods.
result Proposed approach offers insights into approximation errors and accuracy.
Innovative PGMs match neural networks, revealing precise approximations during forward propagation.
problem Lack of precise semantics and probabilistic interpretation in neural networks.
method Constructing infinite tree-structured PGMs that correspond to neural networks.
result DNNs perform precise approximations of PGM inference during forward propagation.
NSOTree combines neural networks and trees for better survival analysis interpretability.
problem Survival analysis event prediction with interpretability.
method Proposes NSOTree integrating neural networks and trees for better interpretability.
result NSOTree improves both performance and interpretability in survival analysis.
Four decades after their invention, quasi-Newton methods are still state of the art in unconstrained numerical optimization. Although not usually interpreted thus, these are learning algorithms that fit a local quadratic approximation to the objective function. We show that many, including the most popular, quasi-Newto…
NSA-Flow optimizes matrix representations for interpretability in complex data.
problem Balancing interpretability and model flexibility in high-dimensional data.
method Non-negative Stiefel Approximating Flow (NSA-Flow) unifies sparse matrix factorization and orthogonalization.
result NSA-Flow yields sparse, stable, and interpretable representations.
The paper connects ABC to GBI, suggesting ABC as a robustification strategy.
problem Approximate Bayesian Computation struggles with tractability in complex simulators.
method Reinterpreting ABC as an implicitly defined error model and suggesting GBI.
result ABC can be seen as a robustification strategy for approximating Bayesian posteriors.
Temporal difference learning explained through gradient splitting, improving convergence times.
problem Learning value functions in Markov Decision Processes with linear approximations.
method Interpreting TD learning as gradient splitting and applying convergence proofs from gradient descent.
result Improved convergence times for TD learning, especially with a minor variation.
This paper reviews methods for discovering patient subgroups from EHR data.
problem Discovering subgroups of patients and co-occurring medical conditions from EHR data.
method Low-rank data approximation methods like matrix and tensor decompositions.
result These methods provide transparent and interpretable insights into patient phenotypes.
New method initializes sigmoidal MLPs for interpretable shapes.
problem Creating interpretable decision boundaries in neural networks.
method Introducing a geometry-aware initialization for sigmoidal multi-layer perceptrons (MLPs) using tropical geometry.
result Sigmoidal MLPs can have decision boundaries aligned with prescribed shapes at initialization.
MRTL learns interpretable spatial patterns efficiently.
problem Efficient and interpretable spatial analysis in various fields.
method Multiresolution Tensor Learning (MRTL) algorithm.
result 4~5x speedup with accurate and interpretable latent factors.
Proposes a new CG interpretation of neural networks for better theoretical analysis.
problem Lack of theoretical analysis in neural networks interpretation.
method Interprets neural networks as chain graphs and feed-forward as approximate inference.
result Provides novel theoretical support and insights for various neural network techniques.
The paper uses model-based trees to create interpretable surrogate models for complex machine learning models.
problem Interpreting complex machine learning models.
method Using model-based trees to partition feature space and create interpretable models.
result Model-based trees generate optimal surrogate models that balance interpretability and performance.
New method learns to encode predictions within interpretations, improving evaluation.
problem Need for interpretable machine learning, but existing methods are slow or lack fidelity.
method Amortized explanation methods that learn a global selector model optimizing fidelity of interpretations.
result Predictions can be encoded within interpretations, detected by EVAL-X.
Current methods to interpret deep learning models by generating saliency maps generally rely on two key assumptions. First, they use first-order approximations of the loss function neglecting higher-order terms such as the loss curvatures. Second, they evaluate each feature's importance in isolation, ignoring their int…
We introduce a new model-agnostic explanation technique which explains the prediction of any classifier called CLE. CLE gives an faithful and interpretable explanation to the prediction, by approximating the model locally using an interpretable model. We demonstrate the flexibility of CLE by explaining different models…
Proposes ANOVA-TPNN for stable interpretation of complex functions.
problem Stability issues in estimating components of functional ANOVA models.
method Introduces ANOVA-TPNN based on tensor product basis expansion.
result ANOVA-TPNN provides stable estimation of components.
Improved scalability and interpretability in training data attribution.
problem Identifying which training data drives specific behaviors, especially unintended ones.
method Leveraging interpretable structures within the model to attribute model behavior to semantic directions, not individual test examples.
result Simple probe-based attribution methods are first-order approximations of Concept Influence that achieve comparable performance while being over an order-of-magnitude faster.
The study predicts Kronecker coefficients using interpretable machine learning models.
problem Predicting Kronecker coefficients of the symmetric group.
method Employed interpretable machine learning models with input features of triples of partitions and b-loadings.
result Achieved an accuracy of approximately 83% and over 99% with transformer-based models.
Understanding black-box machine learning models is crucial for their widespread adoption. Learning globally interpretable models is one approach, but achieving high performance with them is challenging. An alternative approach is to explain individual predictions using locally interpretable models. For locally interpre…
Improves clustering interpretability with decision trees.
problem Hard-to-explain cluster assignments in clustering algorithms.
method Decision tree-based clustering with k-means and k-medians objectives. result An efficient algorithm producing explainable clusters with provable guarantees.
The paper uses transformed ANOVA to identify important fire detection variables.
problem Identifying key variables for forest fire detection.
method Developed a complete orthonormal system for standard normal distribution, applied Z-score transformation, and used ANOVA approximation.
result Attribute ranking reveals important variables for fire detection.