`

( events)   Timezone: »  
Workshop
Mon Dec 13 03:00 AM -- 12:30 PM (PST)
5th Workshop on Meta-Learning
Erin Grant · Fábio Ferreira · Frank Hutter · Jonathan Schwarz · Joaquin Vanschoren · Huaxiu Yao





Workshop Home Page

Recent years have seen rapid progress in meta-learning methods, which transfer knowledge across tasks and domains to efficiently learn new tasks, optimize the learning process itself, and even generate new learning methods from scratch. Meta-learning can be seen as the logical conclusion of the arc that machine learning has undergone in the last decade, from learning classifiers, to learning representations, and finally to learning algorithms that themselves acquire representations, classifiers, and policies for acting in environments. In practice, meta-learning has been shown to yield new state-of-the-art automated machine learning methods, novel deep learning architectures, and substantially improved one-shot learning systems. Moreover, to improve one’s own learning capabilities through experience can also be viewed as a hallmark of intelligent beings, and neuroscience shows a strong connection between human and reward learning and the growing sub-field of meta-reinforcement learning.

Introduction and opening remarks (Live speech)
Ying Wei (Invited talk)
Ying Wei Q&A (Q&A)
Meta-Learning Reliable Priors in the Function Space (Contributed talk)
Poster session 1 (Poster session)
Carlo Ciliberto (Invited talk)
Carlo Ciliberto Q&A (Q&A)
Mihaela Van Der Schaar (Invited talk)
Mihaela Van Der Schaar Q&A (Q&A)
Break
Panel Discussion
Bootstrapped Meta-Learning (Contributed talk)
Nan Rosemary Ke (Invited talk)
Nan Rosemary Ke Q&A (Q&A)
Poster session 2 (Poster session)
Luke Metz (Invited talk)
Luke Metz Q&A (Q&A)
Eleni Triantafillou (Invited talk)
Eleni Triantafillou Q&A (Q&A)
Offline Meta-Reinforcement Learning with Online Self-Supervision (Contributed talk)
Poster session 3 (Poster session)
Task Attended Meta-Learning for Few-Shot Learning (Poster)
Neural Processes with Stochastic Attention: Paying more attention to the context dataset (Poster)
On the Practical Consistency of Meta-Reinforcement Learning Algorithms (Poster)
A Preliminary Study on the Feature Representations of Transfer Learning and Gradient-Based Meta-Learning Techniques (Poster)
Meta-learning inductive biases of learning systems with Gaussian processes (Poster)
Sign-MAML: Efficient Model-Agnostic Meta-Learning by SignSGD (Poster)
Hierarchical Few-Shot Generative Models (Poster)
Transfer Learning for Bayesian HPO with End-to-End Landmark Meta-Features (Poster)
Successor Feature Neural Episodic Control (Poster)
A Meta-Gradient Approach to Learning Cooperative Multi-Agent Communication Topology (Poster)
Transformers Can Do Bayesian-Inference By Meta-Learning on Prior-Data (Poster)
Open-Ended Learning Strategies for Learning Complex Locomotion Skills (Poster)
Unsupervised Meta-Learning via Latent Space Energy-based Model of Symbol Vector Coupling (Poster)
Understanding Catastrophic Forgetting and Remembering in Continual Learning with Optimal Relevance Mapping (Poster)
DARTS without a Validation Set: Optimizing the Marginal Likelihood (Poster)
A Nested Bi-level Optimization Framework for Robust Few Shot Learning (Poster)
One Step at a Time: Pros and Cons of Multi-Step Meta-Gradient Reinforcement Learning (Poster)
Efficient Automated Online Experimentation with Multi-Fidelity (Poster)
Contrastive Embedding of Structured Space for Bayesian Optimization (Poster)
Variational Task Encoders for Model-Agnostic Meta-Learning (Poster)
Introducing Symmetries to Black Box Meta Reinforcement Learning (Poster)
On the Role of Pre-training for Meta Few-Shot Learning (Poster)
How to distribute data across tasks for meta-learning? (Poster)
Meta-learning from sparse recovery (Poster)
Curriculum Meta-Learning for Few-shot Classification (Poster)
FedMix: A Simple and Communication-Efficient Alternative to Local Methods in Federated Learning (Poster)
Skill-based Meta-Reinforcement Learning (Poster)
Effect of diversity in Meta-Learning (Poster)
Few Shot Image Generation via Implicit Autoencoding of Support Sets (Poster)
Studying BatchNorm Learning Rate Decay on Meta-Learning Inner-Loop Adaptation (Poster)