OxCSML : People : Adam R. Kosiorek

Approximate Inference, Deep Generative Models

I am a PhD student supervised by Ingmar Posner and Yee Whye Teh. I am interested in machine reasoning, and mostly in efficient inference in deep generative models, especially for timeseries. I am also excited by attention mechanisms and external memory for neural networks. I received an MSc in Computational Science & Engineering from the Technical University of Munich, where I worked on VAEs with Patrick van der Smagt.

In my free time I train gymnastics and read lots of books.

Publications

2020

J. Xu , J. Ton , H. Kim , A. R. Kosiorek , Y. W. Teh , MetaFun: Meta-Learning with Iterative Functional Updates, in International Conference on Machine Learning (ICML), 2020.
Project: tencent-lsml

We develop a functional encoder-decoder approach to supervised meta-learning, where labeled data is encoded into an infinite-dimensional functional representation rather than a finite-dimensional one. Furthermore, rather than directly producing the representation, we learn a neural update rule resembling functional gradient descent which iteratively improves the representation. The final representation is used to condition the decoder to make predictions on unlabeled data. Our approach is the first to demonstrates the success of encoder-decoder style meta-learning methods like conditional neural processes on large-scale few-shot classification benchmarks such as miniImageNet and tieredImageNet, where it achieves state-of-the-art performance.
```
@inproceedings{xu2019metafun,
  title = {MetaFun: Meta-Learning with Iterative Functional Updates},
  author = {Xu, Jin and Ton, Jean-Francois and Kim, Hyunjik and Kosiorek, Adam R and Teh, Yee Whye},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2020}
}
```

2018

F. Fuchs , O. Groth , A. R. Kosiorek , A. Bewley , M. Wulfmeier , A. Vedaldi , I. Posner , Learning Physics with Neural Stethoscopes, in NeurIPS Workshop on Modeling the Physical World: Learning, Perception, and Control, 2018.

@inproceedings{Fuchs2018learning,
  author = {Fuchs, Fabian and Groth, Olivier and Kosiorek, Adam R. and Bewley, Alex and Wulfmeier, Markus and Vedaldi, Andrea and Posner, Ingmar},
  title = {Learning Physics with Neural Stethoscopes},
  booktitle = {NeurIPS Workshop on Modeling the Physical World: Learning, Perception, and Control},
  year = {2018},
  month = dec
}

T. Rainforth , A. R. Kosiorek , T. A. Le , C. J. Maddison , M. Igl , F. Wood , Y. W. Teh , Tighter Variational Bounds are Not Necessarily Better, in International Conference on Machine Learning (ICML), 2018.
Project: bigbayes

We provide theoretical and empirical evidence that using tighter evidence lower bounds (ELBOs) can be detrimental to the process of learning an inference network by reducing the signal-to-noise ratio of the gradient estimator. Our results call into question common implicit assumptions that tighter ELBOs are better variational objectives for simultaneous model learning and inference amortization schemes. Based on our insights, we introduce three new algorithms: the partially importance weighted auto-encoder (PIWAE), the multiply importance weighted auto-encoder (MIWAE), and the combination importance weighted auto-encoder (CIWAE), each of which includes the standard importance weighted auto-encoder (IWAE) as a special case. We show that each can deliver improvements over IWAE, even when performance is measured by the IWAE target itself. Moreover, PIWAE can simultaneously deliver improvements in both the quality of the inference network and generative network, relative to IWAE.
```
@inproceedings{rainforth2018tighter,
  title = {Tighter Variational Bounds are Not Necessarily Better},
  author = {Rainforth, Tom and Kosiorek, Adam R. and Le, Tuan Anh and Maddison, Chris J. and Igl, Maximilian and Wood, Frank and Teh, Yee Whye},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2018},
  month = jul
}
```
A. R. Kosiorek , H. Kim , Y. W. Teh , I. Posner , Sequential Attend, Infer, Repeat: Generative Modelling of Moving Objects, in Advances in Neural Information Processing Systems (NeurIPS), 2018.
Project: bigbayes

We present Sequential Attend, Infer, Repeat (SQAIR), an interpretable deep generative model for videos of moving objects. It can reliably discover and track objects throughout the sequence of frames, and can also generate future frames conditioning on the current frame, thereby simulating expected motion of objects. This is achieved by explicitly encoding object presence, locations and appearances in the latent variables of the model. SQAIR retains all strengths of its predecessor, Attend, Infer, Repeat (AIR, Eslami et. al., 2016), including learning in an unsupervised manner, and addresses its shortcomings. We use a moving multi-MNIST dataset to show limitations of AIR in detecting overlapping or partially occluded objects, and show how SQAIR overcomes them by leveraging temporal consistency of objects. Finally, we also apply SQAIR to real-world pedestrian CCTV data, where it learns to reliably detect, track and generate walking pedestrians with no supervision.
```
@inproceedings{koskimposteh18,
  title = {Sequential Attend, Infer, Repeat: Generative Modelling of Moving Objects},
  author = {Kosiorek, Adam R. and Kim, Hyunjik and Teh, Yee Whye and Posner, Ingmar},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2018}
}
```

T. A. Le , A. R. Kosiorek , N. Siddharth , Y. W. Teh , F. Wood , Revisiting Reweighted Wake-Sleep, CoRR, vol. abs/1805.10469, 2018.

@article{Le2018RevisitingRW,
  title = {Revisiting Reweighted Wake-Sleep},
  author = {Le, Tuan Anh and Kosiorek, Adam R. and Siddharth, N. and Teh, Yee Whye and Wood, Frank},
  journal = {CoRR},
  year = {2018},
  volume = {abs/1805.10469}
}

F. B. Fuchs , O. Groth , A. R. Kosiorek , A. Bewley , M. Wulfmeier , A. Vedaldi , I. Posner , Neural Stethoscopes: Unifying Analytic, Auxiliary and Adversarial Network Probing, CoRR, vol. abs/1806.05502, 2018.

@article{Fuchs2018NeuralSU,
  title = {Neural Stethoscopes: Unifying Analytic, Auxiliary and Adversarial Network Probing},
  author = {Fuchs, Fabian B. and Groth, Oliver and Kosiorek, Adam R. and Bewley, Alex and Wulfmeier, Markus and Vedaldi, Andrea and Posner, Ingmar},
  journal = {CoRR},
  year = {2018},
  volume = {abs/1806.05502}
}

2017

N. Dhir , A. R. Kosiorek , I. Posner , Bayesian Delay Embeddings for Dynamical Systems, in NIPS Timeseries Workshop, 2017.

@inproceedings{DhirNIPS2017,
  author = {Dhir, Neil and Kosiorek, Adam Roman and Posner, Ingmar},
  title = {Bayesian Delay Embeddings for Dynamical Systems},
  booktitle = {NIPS Timeseries Workshop},
  year = {2017},
  month = dec
}

A. R. Kosiorek , A. Bewley , I. Posner , Hierarchical Attentive Recurrent Tracking, in Neural Information Processing Systems, 2017.

@inproceedings{Kosiorek2017hierarchical,
  title = {Hierarchical Attentive Recurrent Tracking},
  author = {Kosiorek, Adam R and Bewley, Alex and Posner, Ingmar},
  booktitle = {Neural Information Processing Systems},
  year = {2017},
  month = dec
}