Timezone: »
From CNNs to attention mechanisms, encoding inductive biases into neural networks has been a fruitful source of improvement in machine learning. Adding auxiliary losses to the main objective function is a general way of encoding biases that can help networks learn better representations. However, since auxiliary losses are minimized only on training data, they suffer from the same generalization gap as regular task losses. Moreover, by adding a term to the loss function, the model optimizes a different objective than the one we care about. In this work we address both problems: first, we take inspiration from transductive learning and note that after receiving an input but before making a prediction, we can fine-tune our networks on any unsupervised loss. We call this process tailoring, because we customize the model to each input to ensure our prediction satisfies the inductive bias. Second, we formulate meta-tailoring, a nested optimization similar to that in meta-learning, and train our models to perform well on the task objective after adapting them using an unsupervised loss. The advantages of tailoring and meta-tailoring are discussed theoretically and demonstrated empirically on a diverse set of examples.
Author Information
Ferran Alet (MIT)
Maria Bauza (MIT)
I am interested on Robotic Manipulation and Machine Learning
Kenji Kawaguchi (MIT)
Nurullah Giray Kuru (Massachusetts Institute of Technology)
Tomás Lozano-Pérez (MIT)
Leslie Kaelbling (MIT)
More from the Same Authors
-
2020 : Measuring few-shot extrapolation with program induction »
Ferran Alet -
2020 : Tailoring: encoding inductive biases by optimizing unsupervised objectives at prediction time »
Ferran Alet -
2020 : Robotic gripper design with Evolutionary Strategies and Graph Element Networks »
Ferran Alet · Maria Bauza · Adarsh K Jeewajee · Max Thomsen · Alberto Rodriguez · Leslie Kaelbling · Tomás Lozano-Pérez -
2021 : Catastrophic Failures of Neural Active Learning on Heteroskedastic Distributions »
Savya Khosla · Alex Lamb · Jordan Ash · Cyril Zhang · Kenji Kawaguchi -
2021 : Noether Networks: Meta-Learning Useful Conserved Quantities »
Ferran Alet · Dylan Doblar · Allan Zhou · Josh Tenenbaum · Kenji Kawaguchi · Chelsea Finn -
2022 : Solving PDDL Planning Problems with Pretrained Large Language Models »
Tom Silver · Varun Hariprasad · Reece Shuttleworth · Nishanth Kumar · Tomás Lozano-Pérez · Leslie Kaelbling -
2023 : Decentralized agent-based modeling »
Ayush Chopra · Arnau Quera-Bofarull · Nurullah Giray Kuru · Ramesh Raskar -
2023 : Decentralized agent-based modeling »
Ayush Chopra · Arnau Quera-Bofarull · Nurullah Giray Kuru · Ramesh Raskar -
2023 : Compositional Foundation Models for Hierarchical Planning »
Anurag Ajay · Seungwook Han · Yilun Du · Shuang Li · Abhi Gupta · Tommi Jaakkola · Josh Tenenbaum · Leslie Kaelbling · Akash Srivastava · Pulkit Agrawal -
2023 : Compositional Foundation Models for Hierarchical Planning »
Anurag Ajay · Seungwook Han · Yilun Du · Shuang Li · Abhi Gupta · Tommi Jaakkola · Josh Tenenbaum · Leslie Kaelbling · Akash Srivastava · Pulkit Agrawal -
2023 Poster: What Planning Problems Can A Relational Neural Network Solve? »
Jiayuan Mao · Tomás Lozano-Pérez · Josh Tenenbaum · Leslie Kaelbling -
2023 Poster: Compositional Foundation Models for Hierarchical Planning »
Anurag Ajay · Seungwook Han · Yilun Du · Shuang Li · Abhi Gupta · Tommi Jaakkola · Josh Tenenbaum · Leslie Kaelbling · Akash Srivastava · Pulkit Agrawal -
2022 Poster: PDSketch: Integrated Domain Programming, Learning, and Planning »
Jiayuan Mao · Tomás Lozano-Pérez · Josh Tenenbaum · Leslie Kaelbling -
2021 Poster: Adversarial Training Helps Transfer Learning via Better Representations »
Zhun Deng · Linjun Zhang · Kailas Vodrahalli · Kenji Kawaguchi · James Zou -
2021 Poster: Understanding End-to-End Model-Based Reinforcement Learning Methods as Implicit Parameterization »
Clement Gehring · Kenji Kawaguchi · Jiaoyang Huang · Leslie Kaelbling -
2021 Poster: EIGNN: Efficient Infinite-Depth Graph Neural Networks »
Juncheng Liu · Kenji Kawaguchi · Bryan Hooi · Yiwei Wang · Xiaokui Xiao -
2021 Poster: Noether Networks: meta-learning useful conserved quantities »
Ferran Alet · Dylan Doblar · Allan Zhou · Josh Tenenbaum · Kenji Kawaguchi · Chelsea Finn -
2021 Poster: Discrete-Valued Neural Communication »
Dianbo Liu · Alex Lamb · Kenji Kawaguchi · Anirudh Goyal · Chen Sun · Michael Mozer · Yoshua Bengio -
2020 : Spotlight Session 2 »
Augustus Odena · Kensen Shi · David Bieber · Ferran Alet · Charles Sutton · Roshni Iyer -
2020 : Ferran Alet - Tailoring: encoding inductive biases by optimizing unsupervised objectives at prediction time »
Ferran Alet -
2020 Poster: Adversarially-learned Inference via an Ensemble of Discrete Undirected Graphical Models »
Adarsh Keshav Jeewajee · Leslie Kaelbling -
2020 : Doing for our robots what nature did for us »
Leslie Kaelbling -
2019 : Poster Session »
Matthia Sabatelli · Adam Stooke · Amir Abdi · Paulo Rauber · Leonard Adolphs · Ian Osband · Hardik Meisheri · Karol Kurach · Johannes Ackermann · Matt Benatan · GUO ZHANG · Chen Tessler · Dinghan Shen · Mikayel Samvelyan · Riashat Islam · Murtaza Dalal · Luke Harries · Andrey Kurenkov · Konrad Żołna · Sudeep Dasari · Kristian Hartikainen · Ofir Nachum · Kimin Lee · Markus Holzleitner · Vu Nguyen · Francis Song · Christopher Grimm · Felipe Leno da Silva · Yuping Luo · Yifan Wu · Alex Lee · Thomas Paine · Wei-Yang Qu · Daniel Graves · Yannis Flet-Berliac · Yunhao Tang · Suraj Nair · Matthew Hausknecht · Akhil Bagaria · Simon Schmitt · Bowen Baker · Paavo Parmas · Benjamin Eysenbach · Lisa Lee · Siyu Lin · Daniel Seita · Abhishek Gupta · Riley Simmons-Edler · Yijie Guo · Kevin Corder · Vikash Kumar · Scott Fujimoto · Adam Lerer · Ignasi Clavera Gilaberte · Nicholas Rhinehart · Ashvin Nair · Ge Yang · Lingxiao Wang · Sungryull Sohn · J. Fernando Hernandez-Garcia · Xian Yeow Lee · Rupesh Srivastava · Khimya Khetarpal · Chenjun Xiao · Luckeciano Carvalho Melo · Rishabh Agarwal · Tianhe Yu · Glen Berseth · Devendra Singh Chaplot · Jie Tang · Anirudh Srinivasan · Tharun Kumar Reddy Medini · Aaron Havens · Misha Laskin · Asier Mujika · Rohan Saphal · Joseph Marino · Alex Ray · Joshua Achiam · Ajay Mandlekar · Zhuang Liu · Danijar Hafner · Zhiwen Tang · Ted Xiao · Michael Walton · Jeff Druce · Ferran Alet · Zhang-Wei Hong · Stephanie Chan · Anusha Nagabandi · Hao Liu · Hao Sun · Ge Liu · Dinesh Jayaraman · John Co-Reyes · Sophia Sanborn -
2019 : Coffee/Poster session 2 »
Xingyou Song · Puneet Mangla · David Salinas · Zhenxun Zhuang · Leo Feng · Shell Xu Hu · Raul Puri · Wesley Maddox · Aniruddh Raghu · Prudencio Tossou · Mingzhang Yin · Ishita Dasgupta · Kangwook Lee · Ferran Alet · Zhen Xu · Jörg Franke · James Harrison · Jonathan Warrell · Guneet Dhillon · Arber Zela · Xin Qiu · Julien Niklas Siems · Russell Mendonca · Louis Schlessinger · Jeffrey Li · Georgiana Manolache · Debojyoti Dutta · Lucas Glass · Abhishek Singh · Gregor Koehler -
2019 Poster: Neural Relational Inference with Fast Modular Meta-learning »
Ferran Alet · Erica Weng · Tomás Lozano-Pérez · Leslie Kaelbling -
2018 : Discussion Panel: Ryan Adams, Nicolas Heess, Leslie Kaelbling, Shie Mannor, Emo Todorov (moderator: Roy Fox) »
Ryan Adams · Nicolas Heess · Leslie Kaelbling · Shie Mannor · Emo Todorov · Roy Fox -
2018 : On the Value of Knowing What You Don't Know: Learning to Sample and Sampling to Learn for Robot Planning (Leslie Kaelbling) »
Leslie Kaelbling -
2018 : Leslie Kaelbling »
Leslie Kaelbling -
2018 Workshop: Infer to Control: Probabilistic Reinforcement Learning and Structured Control »
Leslie Kaelbling · Martin Riedmiller · Marc Toussaint · Igor Mordatch · Roy Fox · Tuomas Haarnoja -
2018 : Talk 8: Leslie Kaelbling - Learning models of very large hybrid domains »
Leslie Kaelbling -
2018 : Coffee Break 1 (Posters) »
Ananya Kumar · Siyu Huang · Huazhe Xu · Michael Janner · Parth Chadha · Nils Thuerey · Peter Lu · Maria Bauza · Anthony Tompkins · Guanya Shi · Thomas Baumeister · André Ofner · Zhi-Qi Cheng · Yuping Luo · Deepika Bablani · Jeroen Vanbaar · Kartic Subr · Tatiana López-Guevara · Devesh Jha · Fabian Fuchs · Stefano Rosa · Alison Pouplin · Alex Ray · Qi Liu · Eric Crawford -
2018 Poster: Regret bounds for meta Bayesian optimization with an unknown Gaussian process prior »
Zi Wang · Beomjoon Kim · Leslie Kaelbling -
2018 Spotlight: Regret bounds for meta Bayesian optimization with an unknown Gaussian process prior »
Zi Wang · Beomjoon Kim · Leslie Kaelbling -
2016 Poster: Deep Learning without Poor Local Minima »
Kenji Kawaguchi -
2016 Oral: Deep Learning without Poor Local Minima »
Kenji Kawaguchi -
2015 Poster: Bayesian Optimization with Exponential Convergence »
Kenji Kawaguchi · Leslie Kaelbling · Tomás Lozano-Pérez -
2008 Poster: Multi-Agent Filtering with Infinitely Nested Beliefs »
Luke Zettlemoyer · Brian Milch · Leslie Kaelbling -
2008 Spotlight: Multi-Agent Filtering with Infinitely Nested Beliefs »
Luke Zettlemoyer · Brian Milch · Leslie Kaelbling -
2007 Workshop: The Grammar of Vision: Probabilistic Grammar-Based Models for Visual Scene Understanding and Object Categorization »
Virginia Savova · Josh Tenenbaum · Leslie Kaelbling · Alan Yuille