Learning algorithms

A quick guide to Amazon’s papers at ICML 2024

Staff writer

July 17, 2024

Learning algorithms and reinforcement learning are areas of focus, while LLM-related research — on topics such as continual learning, hallucination mitigation, and privacy — remains well represented.

Machine learning

A negative result on gradient matching for selective backprop

Lukas Balles, Cédric Archambeau, Giovanni Zappella

NeurIPS 2023 Workshop on I Can’t Believe It’s Not Better (ICBINB): Failure Modes in the Age of Foundation Models

2023

With increasing scale in model and dataset size, the training of deep neural networks becomes a massive computational burden. One approach to speed up the training process is Selective Backprop. For this approach, we perform a forward pass to obtain a loss value for each data point in a minibatch. The backward pass is then restricted to a subset of that minibatch, prioritizing high-loss examples. We build

Machine learning

On the irrelevance of machine learning algorithms and the importance of relativity

Carlos Huertas, Qi Zhao

IEEE ICME 2023

2023

Information explosion has brought us a wide range of data formats and machine learning keeps in constant evolution to develop mechanisms to extract knowledge from them. Modern models in the Deep Learning space have proven to be very successful in multiple applications, yet in the tabular space they fail to provide consistent competitive performance. However, in this work we claim model selection can become

Machine learning

Meta-learning the difference: Preparing large language models for efficient adaptation

Zejiang Hou, Julian Salazar, George Polovets

Transactions of the Association for Computational Linguistics

2022

Large pretrained language models (PLMs) are often domain- or task-adapted via finetuning or prompting. Finetuning requires modifying all of the parameters and having enough data to avoid overfitting while prompting requires no training and few examples but limits performance. Instead, we prepare PLMs for data- and parameter-efficient adaptation by learning to learn the difference between general and adapted

Conversational AI

Amazon Robotics names initial fellowship program recipients

Staff writer

August 10, 2021

The fellowships are aimed at helping students from underrepresented backgrounds establish careers in robotics, engineering, computer science, and related fields.

Robotics

Meta-Q-Learning

Rasool Fakoor, Pratik Chaudhari, Stefano Soatto, Alex Smola

2020

This paper introduces Meta-Q-Learning (MQL), a new off-policy algorithm for meta-Reinforcement Learning (meta-RL). MQL builds upon three simple ideas. First, we show that Q-learning is competitive with state-of-the-art meta-RL algorithms if given access to a context variable that is a representation of the past trajectory. Second, a multi-task objective to maximize the average reward across the training

Machine learning

How robots can adapt to new tasks — quickly

Rasool Fakoor, Pratik Chaudhari

April 22, 2020

New approach to meta-reinforcement learning minimizes the need for costly interactions with the environment.

Machine learning

Optimal continual learning has perfect memory and is NP-HARD

Jeremias Knoblauch, Hisham Husain, Tom Diethe

ICML 2020

2020

Continual Learning (CL) algorithms incrementally learn a predictor or representation across multiple sequentially observed tasks. Designing CL algorithms that perform reliably and avoid so-called catastrophic forgetting has proven a persistent challenge. The current paper develops a theoretical approach that explains why. In particular, we derive the computational properties which CL algorithms would have

Machine learning

Introducing Alexa for e-learning

Jinjin Zhao, Shreyansh Bhatt, Candace Thille, Dawn Zimmaro, Neelesh Gattani, Josh Walker

ACM L@S 2020

2020

E-learning is becoming popular as it provides learners the flexibility, targeted resources across the internet, personalized guidance, and immediate feedback during learning. However, lack of social interaction, an indispensable component in developing some skills, has been a pain point in e-learning. We propose using Alexa, a voice-controlled Intelligent Personal Assistants (IPA), in e-learning to provide

Conversational AI

Accelerating parallel training of neural nets

Pranav Ladkat

September 05, 2019

Earlier this year, we reported a speech recognition system trained on a million hours of data, a feat possible through semi-supervised learning, in which training data is annotated by machines rather than by people. These sorts of massive machine learning projects are becoming more common, and they require distributing the training process across multiple processors. Otherwise, training becomes too time consuming.

Machine learning

Learning algorithms

Work with us