Related papers: Length Generalization in Arithmetic Transformers
Grokking is the intriguing phenomenon where a model learns to generalize long after it has fit the training data. We show both analytically and numerically that grokking can surprisingly occur in linear networks performing linear tasks in a…
This paper studies how the model architecture and data configurations influence the empirical memorization capacity of generative transformers. The models are trained using synthetic text datasets derived from the Systematized Nomenclature…
Large Transformer models routinely achieve state-of-the-art results on a number of tasks but training these models can be prohibitively costly, especially on long sequences. We introduce two techniques to improve the efficiency of…
Large-scale transformers achieve impressive results on program synthesis benchmarks, yet their true generalization capabilities remain obscured by data contamination and opaque training corpora. To rigorously assess whether models are truly…
Large-scale pretraining instills large amounts of knowledge in deep neural networks. This, in turn, improves the generalization behavior of these models in downstream tasks. What exactly are the limits to the generalization benefits of…
Large-scale Transformer models are known for their exceptional performance in a range of tasks, but training them can be difficult due to the requirement for communication-intensive model parallelism. One way to improve training speed is to…
It has been observed in practice that applying pruning-at-initialization methods to neural networks and training the sparsified networks can not only retain the testing performance of the original dense models, but also sometimes even…
Is it possible to learn policies for robotic assembly that can generalize to new objects? We explore this idea in the context of the kit assembly task. Since classic methods rely heavily on object pose estimation, they often struggle to…
Generalization is a central aspect of learning theory. Here, we propose a framework that explores an auxiliary task-dependent notion of generalization, and attempts to quantitatively answer the following question: given two sets of patterns…
Math reasoning has become the poster child of progress in large language models (LLMs), with new models rapidly surpassing human-level performance on benchmarks like MATH and AIME. But as math leaderboards improve week by week, it is worth…
Recent advances in the field of abstractive summarization leverage pre-trained language models rather than train a model from scratch. However, such models are sluggish to train and accompanied by a massive overhead. Researchers have…
Transformers are the dominant architecture for sequence modeling, but there is growing interest in models that use a fixed-size latent state that does not depend on the sequence length, which we refer to as "generalized state space models"…
We study Transformers on the task \emph{program trace generation} (PTG), where models produce step-by-step execution traces for synthetic programs. Unlike existing algorithmic problems, PTG externalizes reasoning through long traces where…
Trained ML models are commonly embedded in optimization problems. In many cases, this leads to large-scale NLPs that are difficult to solve to global optimality. While ML models frequently lead to large problems, they also exhibit…
Averaging predictions over a set of models -- an ensemble -- is widely used to improve predictive performance and uncertainty estimation of deep learning models. At the same time, many machine learning systems, such as search, matching, and…
Imitation learning is an effective approach for training game-playing agents and, consequently, for efficient game production. However, generalization - the ability to perform well in related but unseen scenarios - is an essential…
Machine Reading Comprehension (MRC) is an active field in natural language processing with many successful developed models in recent years. Despite their high in-distribution accuracy, these models suffer from two issues: high training…
Applying machine learning to tasks that operate with code changes requires their numerical representation. In this work, we propose an approach for obtaining such representations during pre-training and evaluate them on two different…
Deep Learning (DL) models can be used to tackle time series analysis tasks with great success. However, the performance of DL models can degenerate rapidly if the data are not appropriately normalized. This issue is even more apparent when…
Ensembling is a simple and popular technique for boosting evaluation performance by training multiple models (e.g., with different initializations) and aggregating their predictions. This approach is commonly reserved for the largest…