English
Related papers

Related papers: Learning Compositional Functions with Transformers…

200 papers

Recent research has demonstrated that transformers, particularly linear attention models, implicitly execute gradient-descent-like algorithms on data provided in-context during their forward inference step. However, their capability in…

Machine Learning · Computer Science 2024-10-31 Max Vladymyrov , Johannes von Oswald , Mark Sandler , Rong Ge

The Transformer architecture has become a dominant choice in many domains, such as natural language processing and computer vision. Yet, it has not achieved competitive performance on popular leaderboards of graph-level prediction compared…

Machine Learning · Computer Science 2021-11-25 Chengxuan Ying , Tianle Cai , Shengjie Luo , Shuxin Zheng , Guolin Ke , Di He , Yanming Shen , Tie-Yan Liu

Invertible convolutions have been an essential element for building expressive normalizing flow-based generative models since their introduction in Glow. Several attempts have been made to design invertible $k \times k$ convolutions that…

Computer Vision and Pattern Recognition · Computer Science 2023-01-24 Aditya Kallappa , Sandeep Nagar , Girish Varma

Despite their successes, deep learning models struggle with tasks requiring complex reasoning and function composition. We present a theoretical and empirical investigation into the limitations of Structured State Space Models (SSMs) and…

Machine Learning · Computer Science 2025-03-04 Nikola Zubić , Federico Soldá , Aurelio Sulser , Davide Scaramuzza

We study whether a Large Language Model can learn the deterministic sequence of trees generated by the iterated prime factorization of the natural numbers. Each integer is mapped into a rooted planar tree and the resulting sequence $…

Artificial Intelligence · Computer Science 2025-12-02 Alessandro Breccia , Federica Gerace , Marco Lippi , Gabriele Sicuro , Pierluigi Contucci

Transformers, especially the decoder-only variants, are the backbone of most modern large language models; yet we do not have much understanding of their expressive power except for the simple $1$-layer case. Due to the difficulty of…

Machine Learning · Computer Science 2024-12-05 Lijie Chen , Binghui Peng , Hongxun Wu

The stunning empirical successes of neural networks currently lack rigorous theoretical explanation. What form would such an explanation take, in the face of existing complexity-theoretic lower bounds? A first step might be to show that…

Machine Learning · Computer Science 2017-07-18 Le Song , Santosh Vempala , John Wilmes , Bo Xie

Transformers have supplanted recurrent models in a large number of NLP tasks. However, the differences in their abilities to model different syntactic properties remain largely unknown. Past works suggest that LSTMs generalize very well on…

Computation and Language · Computer Science 2020-10-09 Satwik Bhattamishra , Kabir Ahuja , Navin Goyal

We train Transformer-based language models on ten foundational algorithmic tasks and observe pronounced phase transitions in their loss curves that deviate from established power-law scaling trends. Over large ranges of compute, the…

Machine Learning · Computer Science 2026-01-15 Prudhviraj Naidu , Zixian Wang , Leon Bergen , Ramamohan Paturi

The compositional generalization abilities of neural models have been sought after for human-like linguistic competence. The popular method to evaluate such abilities is to assess the models' input-output behavior. However, that does not…

Computation and Language · Computer Science 2025-02-24 Ryoma Kumon , Hitomi Yanaka

Fine-tuned transformer models have shown superior performances in many natural language tasks. However, the large model size prohibits deploying high-performance transformer models on resource-constrained devices. This paper proposes a…

Computation and Language · Computer Science 2024-10-01 Zi Yang , Samridhi Choudhary , Siegfried Kunzmann , Zheng Zhang

In the paper, we propose an effective and efficient Compositional Federated Learning (ComFedL) algorithm for solving a new compositional Federated Learning (FL) framework, which frequently appears in many data mining and machine learning…

Machine Learning · Computer Science 2023-07-28 Feihu Huang , Junyi Li

Representations learnt through deep neural networks tend to be highly informative, but opaque in terms of what information they learn to encode. We introduce an approach to probabilistic modelling that learns to represent data with two…

Machine Learning · Statistics 2019-05-21 Ilya Feige

Recombining known primitive concepts into larger novel combinations is a quintessentially human cognitive capability. Whether large neural models in NLP can acquire this ability while learning from data is an open question. In this paper,…

Computation and Language · Computer Science 2023-08-02 Josef Valvoda , Naomi Saphra , Jonathan Rawski , Adina Williams , Ryan Cotterell

Recent theoretical results in quantum machine learning have demonstrated a general trade-off between the expressive power of quantum neural networks (QNNs) and their trainability; as a corollary of these results, practical exponential…

Quantum Physics · Physics 2026-01-21 Eric R. Anschuetz , Xun Gao

This paper proposes a novel method for learning highly nonlinear, multivariate functions from examples. Our method takes advantage of the property that continuous functions can be approximated by polynomials, which in turn are representable…

Machine Learning · Computer Science 2020-05-05 Sandor Szedmak , Anna Cichonska , Heli Julkunen , Tapio Pahikkala , Juho Rousu

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

Mixed-precision computations are a hallmark of the current stage of AI, driving the progress in large language models towards efficient, locally deployable solutions. This article addresses the floating-point computation of…

Machine Learning · Computer Science 2026-05-08 Stanislav Budzinskiy , Marian Gloser , Tolunay Yilmaz , Ying Hong Tham , Yuanyi Lin , Wenyi Fang , Fan Wu , Philipp Petersen

Neural machine translation (NMT) models are typically trained with fixed-size input and output vocabularies, which creates an important bottleneck on their accuracy and generalization capability. As a solution, various studies proposed…

Computation and Language · Computer Science 2018-05-08 Duygu Ataman , Marcello Federico

Recently, several types of end-to-end speech recognition methods named transformer-transducer were introduced. According to those kinds of methods, transcription networks are generally modeled by transformer-based neural networks, while…

Machine Learning · Computer Science 2020-11-03 Jae-Jin Jeon , Eesung Kim