# Towards a Neural Statistician

arXiv: https://arxiv.org/abs/1606.02185 · HTML: https://mlsanity.com/paper/1606.02185/

## Key facts

- Cited by 121 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Jun 2016.

## Built on by (most cited first, 30 of 121)

- [Transformers in Vision: A Survey](https://mlsanity.com/paper/2101.01169/) (2021)
- [Scaling Vision Transformers to Gigapixel Images via Hierarchical Self-Supervised Learning](https://mlsanity.com/paper/2206.02647/) (2022)
- [Deep Adaptive Design: Amortizing Sequential Bayesian Experimental Design](https://mlsanity.com/paper/2103.02438/) (2021)
- [Proximal Optimal Transport Modeling of Population Dynamics](https://mlsanity.com/paper/2106.06345/) (2021)
- [SetVAE: Learning Hierarchical Composition for Generative Modeling of Set-Structured Data](https://mlsanity.com/paper/2103.15619/) (2021)
- [What to Pre-Train on? Efficient Intermediate Task Selection](https://mlsanity.com/paper/2104.08247/) (2021)
- [Sharp-MAML: Sharpness-Aware Model-Agnostic Meta Learning](https://mlsanity.com/paper/2206.03996/) (2022)
- [Neural ODE Processes](https://mlsanity.com/paper/2103.12413/) (2021)
- [Bayesian Learning via Neural Schr"odinger-F"ollmer Flows](https://mlsanity.com/paper/2111.10510/) (2021)
- [Few-shot Conformal Prediction with Auxiliary Tasks](https://mlsanity.com/paper/2102.08898/) (2021)
- [Self-Supervised Vision Transformers Learn Visual Concepts in Histopathology](https://mlsanity.com/paper/2203.00585/) (2022)
- [A General-Purpose Self-Supervised Model for Computational Pathology](https://mlsanity.com/paper/2308.15474/) (2023)
- [You Never Cluster Alone](https://mlsanity.com/paper/2106.01908/) (2021)
- [Few-Shot Diffusion Models](https://mlsanity.com/paper/2205.15463/) (2022)
- [Neural Auction: End-to-End Learning of Auction Mechanisms for E-Commerce Advertising](https://mlsanity.com/paper/2106.03593/) (2021)
- [Meta-learning approaches for few-shot learning: A survey of recent advances](https://mlsanity.com/paper/2303.07502/) (2023)
- [The Internet of Federated Things (IoFT): A Vision for the Future and In-depth Survey of Data-driven Approaches for Federated Learning](https://mlsanity.com/paper/2111.05326/) (2021)
- [The Neural Process Family: Survey, Applications and Perspectives](https://mlsanity.com/paper/2209.00517/) (2022)
- [Expanding the Deployment Envelope of Behavior Prediction via Adaptive Meta-Learning](https://mlsanity.com/paper/2209.11820/) (2022)
- [How to Train Your MAML to Excel in Few-Shot Classification](https://mlsanity.com/paper/2106.16245/) (2021)
- [Learning Prototype-oriented Set Representations for Meta-Learning](https://mlsanity.com/paper/2110.09140/) (2021)
- [Amortized Variational Inference for Simple Hierarchical Models](https://mlsanity.com/paper/2111.03144/) (2021)
- [Few-Shot Learning with Class Imbalance](https://mlsanity.com/paper/2101.02523/) (2021)
- [Neural Recursive Belief States in Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2102.02274/) (2021)
- [TOHAN: A One-step Approach towards Few-shot Hypothesis Adaptation](https://mlsanity.com/paper/2106.06326/) (2021)
- [Few-Shot Learning with a Strong Teacher](https://mlsanity.com/paper/2107.00197/) (2021)
- [Neural Processes with Stochastic Attention: Paying more attention to the context dataset](https://mlsanity.com/paper/2204.05449/) (2022)
- [Meta-Learning with Less Forgetting on Large-Scale Non-Stationary Task Distributions](https://mlsanity.com/paper/2209.01501/) (2022)
- [Deep Learning for Cross-Domain Few-Shot Visual Recognition: A Survey](https://mlsanity.com/paper/2303.08557/) (2023)
- [Zero-shot Imputation with Foundation Inference Models for Dynamical Systems](https://mlsanity.com/paper/2402.07594/) (2024)

## Abstract (arXiv)

An efficient learner is one who reuses what they already know to tackle a new problem. For a machine learner, this means understanding the similarities amongst datasets. In order to do this, one must take seriously the idea of working with datasets, rather than datapoints, as the key objects to model. Towards this goal, we demonstrate an extension of a variational autoencoder that can learn a method for computing representations, or statistics, of datasets in an unsupervised fashion. The network is trained to produce statistics that encapsulate a generative model for each dataset. Hence the network enables efficient learning from new datasets for both unsupervised and supervised tasks. We show that we are able to learn statistics that can be used for: clustering datasets, transferring generative models to new datasets, selecting representative samples of datasets and classifying previously unseen classes. We refer to our model as a neural statistician, and by this we mean a neural network that can learn to compute summary statistics of datasets without supervision.