English
Related papers

Related papers: Learning Spectral Methods by Transformers

200 papers

This paper presents Mixed Formal Learning, a new architecture that learns models based on formal mathematical representations of the domain of interest and exposes latent variables. The second element in the architecture learns a particular…

Artificial Intelligence · Computer Science 2019-01-23 Sandra Carrico

Transformer-based pretrained language models (T-PTLMs) have achieved great success in almost every NLP task. The evolution of these models started with GPT and BERT. These models are built on the top of transformers, self-supervised…

Computation and Language · Computer Science 2021-08-31 Katikapalli Subramanyam Kalyan , Ajit Rajasekharan , Sivanesan Sangeetha

Trained transformer models have been found to implement interpretable procedures for tasks like arithmetic and associative recall, but little is understood about how the circuits that implement these procedures originate during training. To…

Machine Learning · Computer Science 2024-10-08 Ziqian Zhong , Jacob Andreas

Efficient training and inference algorithms, such as low-rank adaption and model pruning, have shown impressive performance for learning Transformer-based large foundation models. However, due to the technical challenges of the non-convex…

Machine Learning · Computer Science 2024-06-26 Hongkang Li , Meng Wang , Shuai Zhang , Sijia Liu , Pin-Yu Chen

An increasingly popular machine learning paradigm is to pretrain a neural network (NN) on many tasks offline, then adapt it to downstream tasks, often by re-training only the last linear layer of the network. This approach yields strong…

Machine Learning · Computer Science 2024-06-10 Liam Collins , Hamed Hassani , Mahdi Soltanolkotabi , Aryan Mokhtari , Sanjay Shakkottai

Model-free reinforcement learning algorithms have exhibited great potential in solving single-task sequential decision-making problems with high-dimensional observations and long horizons, but are known to be hard to generalize across…

Machine Learning · Computer Science 2023-05-30 Boyuan Chen , Chuning Zhu , Pulkit Agrawal , Kaiqing Zhang , Abhishek Gupta

The Transformer is an extremely powerful and prominent deep learning architecture. In this work, we challenge the commonly held belief in deep learning that going deeper is better, and show an alternative design approach that is building…

Machine Learning · Computer Science 2022-11-10 Jason Ross Brown , Yiren Zhao , Ilia Shumailov , Robert D Mullins

Multilayer transformer networks consist of interleaved self-attention and feedforward sublayers. Could ordering the sublayers in a different pattern lead to better performance? We generate randomly ordered transformers and train them with…

Computation and Language · Computer Science 2020-04-24 Ofir Press , Noah A. Smith , Omer Levy

Self-supervised models have been shown to produce comparable or better visual representations than their supervised counterparts when trained offline on unlabeled data at scale. However, their efficacy is catastrophically reduced in a…

Computer Vision and Pattern Recognition · Computer Science 2022-04-04 Enrico Fini , Victor G. Turrisi da Costa , Xavier Alameda-Pineda , Elisa Ricci , Karteek Alahari , Julien Mairal

We investigate the capability of a transformer pretrained on natural language to generalize to other modalities with minimal finetuning -- in particular, without finetuning of the self-attention and feedforward layers of the residual…

Machine Learning · Computer Science 2021-07-01 Kevin Lu , Aditya Grover , Pieter Abbeel , Igor Mordatch

Standard meta-learning for representation learning aims to find a common representation to be shared across multiple tasks. The effectiveness of these methods is often limited when the nuances of the tasks' distribution cannot be captured…

Machine Learning · Computer Science 2021-03-31 Giulia Denevi , Massimiliano Pontil , Carlo Ciliberto

We use machine learning to classify examples of braids (or flat braids) as trivial or non-trivial. Our ML takes form of supervised learning using neural networks (multilayer perceptrons). When they achieve good results in classification, we…

Geometric Topology · Mathematics 2023-07-25 Alexei Lisitsa , Mateo Salles , Alexei Vernitski

In this paper we derive an efficient algorithm to learn the parameters of structured predictors in general graphical models. This algorithm blends the learning and inference tasks, which results in a significant speedup over traditional…

Machine Learning · Computer Science 2013-09-02 Tamir Hazan , Alexander Schwing , David McAllester , Raquel Urtasun

An important development in deep learning from the earliest MLPs has been a move towards architectures with structural inductive biases which enable the model to keep distinct sources of information and routes of processing well-separated.…

Machine Learning · Computer Science 2021-03-02 Alex Lamb , Di He , Anirudh Goyal , Guolin Ke , Chien-Feng Liao , Mirco Ravanelli , Yoshua Bengio

Transformers have achieved state-of-the-art performance in language modeling tasks. However, the reasons behind their tremendous success are still unclear. In this paper, towards a better understanding, we train a Transformer model on a…

Machine Learning · Statistics 2024-06-06 Michael E. Sander , Raja Giryes , Taiji Suzuki , Mathieu Blondel , Gabriel Peyré

Transformers have a remarkable ability to learn and execute tasks based on examples provided within the input itself, without explicit prior training. It has been argued that this capability, known as in-context learning (ICL), is a…

Machine Learning · Statistics 2025-10-06 Yue M. Lu , Mary I. Letey , Jacob A. Zavatone-Veth , Anindita Maiti , Cengiz Pehlevan

Due to its empirical success in few-shot classification and reinforcement learning, meta-learning has recently received significant interest. Meta-learning methods leverage data from previous tasks to learn a new task in a sample-efficient…

Machine Learning · Computer Science 2024-07-24 Oğuz Kaan Yüksel , Etienne Boursier , Nicolas Flammarion

We propose split-brain autoencoders, a straightforward modification of the traditional autoencoder architecture, for unsupervised representation learning. The method adds a split to the network, resulting in two disjoint sub-networks. Each…

Computer Vision and Pattern Recognition · Computer Science 2017-04-21 Richard Zhang , Phillip Isola , Alexei A. Efros

Drawing the quantum phase diagram of a many-body system in the parameter space of its Hamiltonian can be seen as a learning problem, which implies labelling the corresponding ground states according to some classification criterium that…

Quantum Physics · Physics 2025-10-17 Mehran Khosrojerdi , Alessandro Cuccoli , Paola Verrucchi , Leonardo Banchi

While humans and animals learn incrementally during their lifetimes and exploit their experience to solve new tasks, standard deep reinforcement learning methods specialize to solve only one task at a time. As a result, the information they…

Artificial Intelligence · Computer Science 2022-02-23 Diego Gomez , Nicanor Quijano , Luis Felipe Giraldo