English
Related papers

Related papers: Algorithmic Task Capture, Computational Complexity…

200 papers

We study inductive bias in Transformers in the infinitely over-parameterized Gaussian process limit and argue transformers tend to be biased towards more permutation symmetric functions in sequence space. We show that the representation…

Machine Learning · Computer Science 2024-05-29 Itay Lavie , Guy Gur-Ari , Zohar Ringel

Much research in machine learning involves finding appropriate inductive biases (e.g. convolutional neural networks, momentum-based optimizers, transformers) to promote generalization on tasks. However, quantification of the amount of…

Machine Learning · Computer Science 2024-06-25 Akhilan Boopathy , William Yue , Jaedong Hwang , Abhiram Iyer , Ila Fiete

Transformer-based models excel in various tasks but their generalization capabilities, especially in arithmetic reasoning, remain incompletely understood. Arithmetic tasks provide a controlled framework to explore these capabilities, yet…

Machine Learning · Computer Science 2025-08-07 Xingcheng Xu , Zibo Zhao , Haipeng Zhang , Yanqing Yang

We consider the learning of algorithmic tasks by mere observation of input-output pairs. Rather than studying this as a black-box discrete regression problem with no assumption whatsoever on the input-output mapping, we concentrate on tasks…

Machine Learning · Computer Science 2018-10-16 Alex Nowak-Vila , David Folqué , Joan Bruna

Large language models exhibit surprising emergent generalization properties, yet also struggle on many simple reasoning tasks such as arithmetic and parity. This raises the question of if and when Transformer models can learn the true…

Machine Learning · Computer Science 2023-10-25 Hattie Zhou , Arwen Bradley , Etai Littwin , Noam Razin , Omid Saremi , Josh Susskind , Samy Bengio , Preetum Nakkiran

People solve different problems and know that some of them are simple, some are complex and some insoluble. The main goal of this work is to develop a mathematical theory of algorithmic complexity for problems. This theory is aimed at…

Computational Complexity · Computer Science 2008-07-08 Mark Burgin

Mechanistic interpretability aims to reverse engineer neural networks by uncovering which high-level algorithms they implement. Causal abstraction provides a precise notion of when a network implements an algorithm, i.e., a causal model of…

Machine Learning · Computer Science 2025-03-17 Theodora-Mara Pîslar , Sara Magliacane , Atticus Geiger

Transformer networks have seen great success in natural language processing and machine vision, where task objectives such as next word prediction and image classification benefit from nuanced context sensitivity across high-dimensional…

Machine Learning · Computer Science 2022-12-13 Yuxuan Li , James L. McClelland

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

In open-ended continuous environments, robots need to learn multiple parameterised control tasks in hierarchical reinforcement learning. We hypothesise that the most complex tasks can be learned more easily by transferring knowledge from…

Artificial Intelligence · Computer Science 2021-02-22 Nicolas Duminy , Sao Mai Nguyen , Junshuai Zhu , Dominique Duhaut , Jerome Kerdreux

Models often need to be constrained to a certain size for them to be considered interpretable. For example, a decision tree of depth 5 is much easier to understand than one of depth 50. Limiting model size, however, often reduces accuracy.…

Machine Learning · Computer Science 2020-07-02 Abhishek Ghose , Balaraman Ravindran

The measure of a machine learning algorithm is the difficulty of the tasks it can perform, and sufficiently difficult tasks are critical drivers of strong machine learning models. However, quantifying the generalization difficulty of…

Machine Learning · Computer Science 2023-06-06 Akhilan Boopathy , Kevin Liu , Jaedong Hwang , Shu Ge , Asaad Mohammedsaleh , Ila Fiete

Despite the recent success of artificial neural networks on a variety of tasks, we have little knowledge or control over the exact solutions these models implement. Instilling inductive biases -- preferences for some solutions over others…

Machine Learning · Computer Science 2024-02-02 Enyan Zhang , Michael A. Lepori , Ellie Pavlick

Can transformers generalize efficiently on problems that require dealing with examples with different levels of difficulty? We introduce a new task tailored to assess generalization over different complexities and present results that…

Recent progress in robotic manipulation has dealt with the case of previously unknown objects in the context of relatively simple tasks, such as bin-picking. Existing methods for more constrained problems, however, such as deliberate…

Robotics · Computer Science 2020-06-30 Chaitanya Mitash , Rahul Shome , Bowen Wen , Abdeslam Boularias , Kostas Bekris

An essential goal in mechanistic interpretability to decode a network, i.e., to convert a neural network's raw weights to an interpretable algorithm. Given the difficulty of the decoding problem, progress has been made to understand the…

Machine Learning · Computer Science 2023-12-07 Isaac Liao , Ziming Liu , Max Tegmark

Algorithm extraction aims to synthesize executable programs directly from models trained on algorithmic tasks, enabling de novo algorithm discovery without relying on human-written code. However, applying this paradigm to Transformer is…

Machine Learning · Computer Science 2026-03-20 Yifan Zhang , Wei Bi , Kechi Zhang , Dongming Jin , Jie Fu , Zhi Jin

Evaluating machine learning models is crucial not only for determining their technical accuracy but also for assessing their potential societal implications. While the potential for low-sample-size bias in algorithms is well known, we…

Machine Learning · Computer Science 2025-05-08 Jarren Briscoe , Garrett Kepler , Daryl Deford , Assefaw Gebremedhin

Borrowing from the transformer models that revolutionized the field of natural language processing, self-supervised feature learning for visual tasks has also seen state-of-the-art success using these extremely deep, isotropic networks.…

Computer Vision and Pattern Recognition · Computer Science 2021-06-01 George Cazenavette , Simon Lucey

Transformers often struggle with length generalization, meaning they fail to generalize to sequences longer than those encountered during training. While arithmetic tasks are commonly used to study length generalization, certain tasks are…

Machine Learning · Computer Science 2025-04-18 Hanseul Cho , Jaeyoung Cha , Srinadh Bhojanapalli , Chulhee Yun
‹ Prev 1 2 3 10 Next ›