# Variational Information Pursuit for Interpretable Predictions

arXiv: https://arxiv.org/abs/2302.02876 · HTML: https://mlsanity.com/paper/2302.02876/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- Builds on 43 of its 61 references that are in the map.
- First posted on arXiv 6 Feb 2023.

## Builds on (most cited first, 30 of 43)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms](https://mlsanity.com/paper/1708.07747/) (2017)
- [Auto-Encoding Variational Bayes](https://mlsanity.com/paper/1312.6114/) (2013)
- [Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps](https://mlsanity.com/paper/1312.6034/) (2013)
- [Visualizing and Understanding Convolutional Networks](https://mlsanity.com/paper/1311.2901/) (2013)
- [Learning Important Features Through Propagating Activation Differences](https://mlsanity.com/paper/1704.02685/) (2017)
- [Sanity Checks for Saliency Maps](https://mlsanity.com/paper/1810.03292/) (2018)
- [SmoothGrad: removing noise by adding noise](https://mlsanity.com/paper/1706.03825/) (2017)
- [Concept Bottleneck Models](https://mlsanity.com/paper/2007.04612/) (2020)
- [On the Convergence of Adam and Beyond](https://mlsanity.com/paper/1904.09237/) (2019)
- [Towards Robust Interpretability with Self-Explaining Neural Networks](https://mlsanity.com/paper/1806.07538/) (2018)
- [Fooling LIME and SHAP: Adversarial Attacks on Post hoc Explanation Methods](https://mlsanity.com/paper/1911.02508/) (2019)
- [Deep Layer Aggregation](https://mlsanity.com/paper/1707.06484/) (2017)
- [Deep Learning for Classical Japanese Literature](https://mlsanity.com/paper/1812.01718/) (2018)
- [Recurrent Models of Visual Attention](https://mlsanity.com/paper/1406.6247/) (2014)
- [The (Un)reliability of saliency methods](https://mlsanity.com/paper/1711.00867/) (2017)
- [On Completeness-aware Concept-Based Explanations in Deep Neural Networks](https://mlsanity.com/paper/1910.07969/) (2019)
- [Deep Learning for Case-Based Reasoning through Prototypes: A Neural Network that Explains Its Predictions](https://mlsanity.com/paper/1710.04806/) (2017)
- [Neural Prototype Trees for Interpretable Fine-grained Image Recognition](https://mlsanity.com/paper/2012.02046/) (2020)
- [Deformable ProtoPNet: An Interpretable Image Classifier Using Deformable Prototypes](https://mlsanity.com/paper/2111.15000/) (2021)
- [Benchmarking Attribution Methods with Relative Feature Importance](https://mlsanity.com/paper/1907.09701/) (2019)

## Built on by (most cited first, 25 of 25)

- [Estimating Conditional Mutual Information for Dynamic Feature Selection](https://mlsanity.com/paper/2306.03301/) (2023)
- [Stochastic Amortization: A Unified Approach to Accelerate Feature and Data Attribution](https://mlsanity.com/paper/2401.15866/) (2024)
- [A Survey on Active Feature Acquisition Strategies](https://mlsanity.com/paper/2502.11067/) (2025)
- [Object Centric Concept Bottlenecks](https://mlsanity.com/paper/2505.24492/) (2025)
- [Stochastic Encodings for Active Feature Acquisition](https://mlsanity.com/paper/2508.01957/) (2025)
- [AFABench: A Generic Framework for Benchmarking Active Feature Acquisition](https://mlsanity.com/paper/2508.14734/) (2025)
- [3VL: Using Trees to Improve Vision-Language Models' Interpretability](https://mlsanity.com/paper/2312.17345/) (2023)
- [Conformal Information Pursuit for Interactively Guiding Large Language Models](https://mlsanity.com/paper/2507.03279/) (2025)
- [Learning Interpretable Queries for Explainable Image Classification with Information Pursuit](https://mlsanity.com/paper/2312.11548/) (2023)
- [Learning-To-Measure: In-Context Active Feature Acquisition](https://mlsanity.com/paper/2510.12624/) (2025)
- [Contextual Knowledge Pursuit for Faithful Visual Synthesis](https://mlsanity.com/paper/2311.17898/) (2023)
- [IP-CRR: Information Pursuit for Interpretable Classification of Chest Radiology Reports](https://mlsanity.com/paper/2505.00191/) (2025)
- [Model-Agnostic Dynamic Feature Selection with Uncertainty Quantification](https://mlsanity.com/paper/2508.02566/) (2025)
- [Weakly Supervised Concept Learning with Class-Level Priors for Interpretable Medical Diagnosis](https://mlsanity.com/paper/2511.01131/) (2025)
- [Hierarchical Concept Embedding & Pursuit for Interpretable Image Classification](https://mlsanity.com/paper/2602.11448/) (2026)
- [Non-Myopic Active Feature Acquisition via Pathwise Policy Gradients](https://mlsanity.com/paper/2605.05511/) (2026)
- [Variational Information Pursuit with Large Language and Multimodal Models for Interpretable Predictions](https://mlsanity.com/paper/2308.12562/) (2023)
- [LIPEx-Locally Interpretable Probabilistic Explanations-To Look Beyond The True Class](https://mlsanity.com/paper/2310.04856/) (2023)
- [Enhancing Performance of Explainable AI Models with Constrained Concept Refinement](https://mlsanity.com/paper/2502.06775/) (2025)
- [Direct Preference Optimization for Adaptive Concept-based Explanations](https://mlsanity.com/paper/2505.15626/) (2025)
- [Uncertainty-Aware Information Pursuit for Interpretable and Reliable Medical Image Analysis](https://mlsanity.com/paper/2506.16742/) (2025)
- [Neural Concept Verifier: Scaling Prover-Verifier Games via Concept Encodings](https://mlsanity.com/paper/2507.07532/) (2025)
- [GenZ: Foundational models as latent variable generators within traditional statistical models](https://mlsanity.com/paper/2512.24834/) (2025)
- [Hypernetworks for Dynamic Feature Selection](https://mlsanity.com/paper/2605.12278/) (2026)
- [Explanations-Driven Active Feature Acquisition for Algorithmic Recourse](https://mlsanity.com/paper/2609.12179/) (2026)

## Abstract (arXiv)

There is a growing interest in the machine learning community in developing predictive algorithms that are "interpretable by design". Towards this end, recent work proposes to make interpretable decisions by sequentially asking interpretable queries about data until a prediction can be made with high confidence based on the answers obtained (the history). To promote short query-answer chains, a greedy procedure called Information Pursuit (IP) is used, which adaptively chooses queries in order of information gain. Generative models are employed to learn the distribution of query-answers and labels, which is in turn used to estimate the most informative query. However, learning and inference with a full generative model of the data is often intractable for complex tasks. In this work, we propose Variational Information Pursuit (V-IP), a variational characterization of IP which bypasses the need for learning generative models. V-IP is based on finding a query selection strategy and a classifier that minimizes the expected cross-entropy between true and predicted labels. We then demonstrate that the IP strategy is the optimal solution to this problem. Therefore, instead of learning generative models, we can use our optimal strategy to directly pick the most informative query given any history. We then develop a practical algorithm by defining a finite-dimensional parameterization of our strategy and classifier using deep networks and train them end-to-end using our objective. Empirically, V-IP is 10-100x faster than IP on different Vision and NLP tasks with competitive performance. Moreover, V-IP finds much shorter query chains when compared to reinforcement learning which is typically used in sequential-decision-making problems. Finally, we demonstrate the utility of V-IP on challenging tasks like medical diagnosis where the performance is far superior to the generative modelling approach.