AMTL 2019

Overview Driven by progress in deep learning, the machine learning community is now able to tackle increasingly more complex problems—ranging from multi-modal reasoning to dexterous robotic manipulation—all of which typically involve solving nontrivial combinations of tasks. We believe that designing adaptive models and algorithms that can efficiently learn, master, and combine multiple tasks is the next frontier. Establishing connections between approaches developed for seemingly different problems is particularly useful for analyzing the landscape of multitask learning techniques. For instance, the compositionality of language tasks motivates modular architectures, which can also be used to construct modular policies in order to tackle the compositional structure of robotic manipulation. Similarly, ideas from personalization in recommender systems (where serving different users can be regarded as different tasks) might perhaps be effective when applied to learning problems in health...

3 mentions: @atalwalkar@pliang279@DSakya
Date: 2019/06/12 17:16

Referring Tweets

@atalwalkar Exciting work by @khodakmoments on theory for gradient-based meta learning (think MAML, Reptile, or even FedAvg) at #ICML2019. Check out Misha's poster tonight (Poster 253), as well as my talk at the AMTL workshop ( on Saturday at 1:45pm.
@pliang279 2. Adaptive and Multitask Learning: Algorithms & Systems Sat Jun 15th 08:30 AM - 06:00 PM @ Seaside Ballroom @eaplatanios @alshedivat @mldcmu @LTIatCMU
@DSakya Presenting two papers at #icml2019 workshops - “Lifelong learning with online leverage score sampling” at & “Model-based deep RL for financial portfolio optimization” at If you are attending, please stop by to discuss.