Learning Flat Latent Manifolds with VAEs
Jul 12, 2020
Speakers
Nutan Chen
Speaker · 0 followers
Alexej Klushyn
Speaker · 0 followers
Francesco Ferroni
Speaker · 0 followers
Justin Bayer
Speaker · 0 followers
Patrick van der Smagt
Speaker · 1 follower
About
Measuring the similarity between data points often requires domain knowledge. This can in parts be compensated by relying on unsupervised methods such as latent-variable models, where similarity/distance is estimated in a more compact latent space. Prevalent is the use of the Euclidean metric, which has the drawback of ignoring information about similarity of data stored in the decoder, as captured by the framework of Riemannian geometry. Alternatives—such as approximating the geodesic—are often computationally inefficient, rendering the methods impractical. We propose an extension to the framework of variational auto-encoders that allows the model to learn flat latent manifolds, where the Euclidean metric is a proxy for the similarity between data points. This is achieved by defining the latent space as a Riemannian manifold and by regularising the metric tensor to be a scaled identity matrix. Additionally, we replace the compact prior typically used in variational auto-encoders with a recently presented, more expressive hierarchical one—and formulate the learning problem as a constrained optimisation problem. We evaluate our method on a range of datasets, including a video-tracking benchmark, where the performance of our unsupervised approach nears that of state-of-the-art supervised approaches, while retaining the computational efficiency of straight-line-based approaches.Measuring the similarity between data points often requires domain knowledge. This can in parts be compensated by relying on unsupervised methods such as latent-variable models, where similarity/distance is estimated in a more compact latent space. Prevalent is the use of the Euclidean metric, which has the drawback of ignoring information about similarity of data stored in the decoder, as captured by the framework of Riemannian geometry. Alternatives—such as approximating the geodesic—are often…
Categories
AI & Data Science
Category · 10.8k presentations
About ICML 2020
The International Conference on Machine Learning (ICML) is the premier gathering of professionals dedicated to the advancement of the branch of artificial intelligence known as machine learning. ICML is globally renowned for presenting and publishing cutting-edge research on all aspects of machine learning used in closely related areas like artificial intelligence, statistics and data science, as well as important application areas such as machine vision, computational biology, speech recognition, and robotics. ICML is one of the fastest growing artificial intelligence conferences in the world. Participants at ICML span a wide range of backgrounds, from academic and industrial researchers, to entrepreneurs and engineers, to graduate students and postdocs.
Like the format? Trust SlidesLive to capture your next event!
Professional recording and live streaming, delivered globally.
Sharing
Recommended Videos
Presentations on similar topic, category or speaker
A Simple Setting for Understanding NAS with Weight-Sharing
Watch later
Misha Khodak, …
Refined bounds for algorithm configuration: The knife-edge of dual class approximability
Watch later
Nina Balcan, …
Local Search is SotA for NAS Benchmarks
Watch later
Sam Nolen, …
T-GD: Transferable GAN-generated Images Detection Framework
Watch later
