English
Related papers

Related papers: Setting the Record Straight on Transformer Oversmo…

200 papers

The remarkable capability of Transformers to do reasoning and few-shot learning, without any fine-tuning, is widely conjectured to stem from their ability to implicitly simulate a multi-step algorithms -- such as gradient descent -- with…

Machine Learning · Computer Science 2024-10-14 Khashayar Gatmiry , Nikunj Saunshi , Sashank J. Reddi , Stefanie Jegelka , Sanjiv Kumar

Transformers are deep neural network architectures that underpin the recent successes of large language models. Unlike more classical architectures that can be viewed as point-to-point maps, a Transformer acts as a measure-to-measure map…

Optimization and Control · Mathematics 2026-02-16 Borjan Geshkovski , Philippe Rigollet , Domènec Ruiz-Balet

Recent research in neural networks and machine learning suggests that using many more parameters than strictly required by the initial complexity of a regression problem can result in more accurate or faster-converging models -- contrary to…

Machine Learning · Computer Science 2023-05-18 Arthur Castello B. de Oliveira , Milad Siami , Eduardo D. Sontag

Transformer based large-language models (LLMs) display extreme proficiency with language yet a precise understanding of how they work remains elusive. One way of demystifying transformer predictions would be to describe how they depend on…

Computation and Language · Computer Science 2024-11-06 Timothy Nguyen

Humans are able to seamlessly visually imitate others, by inferring their intentions and using past experience to achieve the same end goal. In other words, we can parse complex semantic knowledge from raw video and efficiently translate…

Machine Learning · Computer Science 2020-11-12 Sudeep Dasari , Abhinav Gupta

Over-smoothing is a severe problem which limits the depth of Graph Convolutional Networks. This article gives a comprehensive analysis of the mechanism behind Graph Convolutional Networks and the over-smoothing effect. The article proposes…

Machine Learning · Computer Science 2022-02-02 Fang Sun

We study the problem of length generalization (LG) in transformers: the ability of a model trained on shorter sequences to maintain performance when evaluated on much longer, previously unseen inputs. Prior work by Huang et al. (2025)…

Machine Learning · Computer Science 2025-11-03 Zachary Izzo , Eshaan Nichani , Jason D. Lee

Large language models (LLMs) achieve strong performance but incur high deployment costs, motivating extremely low-bit but lossy quantization. Existing quantization algorithms mainly focus on improving the numerical accuracy of forward…

Computation and Language · Computer Science 2026-05-18 Yuzhuang Xu , Xu Han , Yuxuan Li , Pengzhan Li , Wanxiang Che

Transformers have shown improved performance when compared to previous architectures for sequence processing such as RNNs. Despite their sizeable performance gains, as recently suggested, the model is computationally expensive to train and…

Computation and Language · Computer Science 2021-09-09 Machel Reid , Edison Marrese-Taylor , Yutaka Matsuo

Transformers have significantly advanced the field of natural language processing, but comprehending their internal mechanisms remains a challenge. In this paper, we introduce a novel geometric perspective that elucidates the inner…

Computation and Language · Computer Science 2023-09-20 Raul Molina

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

Spectral variability in hyperspectral images can result from factors including environmental, illumination, atmospheric and temporal changes. Its occurrence may lead to the propagation of significant estimation errors in the unmixing…

Computer Vision and Pattern Recognition · Computer Science 2020-01-23 Ricardo Augusto Borsoi , Tales Imbiriba , José Carlos Moreira Bermudez

Transformer-based architectures achieved breakthrough performance in natural language processing and computer vision, yet they remain inferior to simpler linear baselines in multivariate long-term forecasting. To better understand this…

Machine Learning · Computer Science 2024-06-04 Romain Ilbert , Ambroise Odonnat , Vasilii Feofanov , Aladin Virmaux , Giuseppe Paolo , Themis Palpanas , Ievgen Redko

Understanding how information propagates through Transformer models is a key challenge for interpretability. In this work, we study the effects of minimal token perturbations on the embedding space. In our experiments, we analyze the…

Machine Learning · Computer Science 2025-06-24 Eddie Conti , Alejandro Astruc , Alvaro Parafita , Axel Brando

In the context of neural network models, overparametrization refers to the phenomena whereby these models appear to generalize well on the unseen data, even though the number of parameters significantly exceeds the sample sizes, and the…

Machine Learning · Statistics 2020-03-25 Matt Emschwiller , David Gamarnik , Eren C. Kızıldağ , Ilias Zadik

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

The increasing reliance on ML models in high-stakes tasks has raised a major concern on fairness violations. Although there has been a surge of work that improves algorithmic fairness, most of them are under the assumption of an identical…

Machine Learning · Computer Science 2023-01-18 Bang An , Zora Che , Mucong Ding , Furong Huang

Despite being able to capture a range of features of the data, high accuracy models trained with supervision tend to make similar predictions. This seemingly implies that high-performing models share similar biases regardless of training…

Machine Learning · Computer Science 2022-04-27 Raphael Gontijo-Lopes , Yann Dauphin , Ekin D. Cubuk

A recent body of work has demonstrated that Transformer embeddings can be linearly decomposed into well-defined sums of factors, that can in turn be related to specific network inputs or components. There is however still a dearth of work…

Computation and Language · Computer Science 2023-10-12 Timothee Mickus , Raúl Vázquez

The pretrain-finetune paradigm usually improves downstream performance over training a model from scratch on the same task, becoming commonplace across many areas of machine learning. While pretraining is empirically observed to be…

Computer Vision and Pattern Recognition · Computer Science 2023-07-13 Gabriele Merlin , Vedant Nanda , Ruchit Rawal , Mariya Toneva
‹ Prev 1 3 4 5 6 7 10 Next ›