English
Related papers

Related papers: The Garden of Forking Paths: Observing Dynamic Par…

200 papers

Deep neural networks often contain far more parameters than training examples, yet they still manage to generalize well in practice. Classical complexity measures such as VC-dimension or PAC-Bayes bounds usually become vacuous in this…

Machine Learning · Computer Science 2025-08-26 Aviral Dhingra

Molecular Property Prediction (MPP) is vital for drug discovery, crop protection, and environmental science. Over the last decades, diverse computational techniques have been developed, from using simple physical and chemical properties and…

Machine Learning · Computer Science 2024-04-08 Afnan Sultan , Jochen Sieg , Miriam Mathea , Andrea Volkamer

Next-token prediction (NTP) over large text corpora has become the go-to paradigm to train large language models. Yet, it remains unclear how NTP influences the mapping of linguistic patterns to geometric properties of the resulting model…

Computation and Language · Computer Science 2025-02-20 Yize Zhao , Tina Behnia , Vala Vakilian , Christos Thrampoulidis

State-of-the-art results in large language models (LLMs) often rely on scale, which becomes computationally expensive. This has sparked a research agenda to reduce these models' parameter counts and computational costs without significantly…

Computation and Language · Computer Science 2024-11-07 Xiuying Wei , Skander Moalla , Razvan Pascanu , Caglar Gulcehre

Is it possible to develop a `physics of language' which can explain the spatial, temporal and social patterns we see, and which can predict future change like we forecast the weather? Such a theory is likely to involve ideas from…

Physics and Society · Physics 2025-12-22 James Burridge

Use of machine learning to perform database operations, such as indexing, cardinality estimation, and sorting, is shown to provide substantial performance benefits. However, when datasets change and data distribution shifts, empirical…

Machine Learning · Computer Science 2024-11-12 Sepanta Zeighami , Cyrus Shahahbi

Large language models (LLMs) learn non-trivial abstractions during pretraining, such as detecting irregular plural noun subjects. However, because traditional evaluation methods (e.g., benchmarking) fail to reveal how models acquire these…

Computation and Language · Computer Science 2026-05-01 Deniz Bayazit , Aaron Mueller , Antoine Bosselut

We study parameter estimation in Nonlinear Factor Analysis (NFA) where the generative model is parameterized by a deep neural network. Recent work has focused on learning such models using inference (or recognition) networks; we identify a…

Machine Learning · Statistics 2017-10-18 Rahul G. Krishnan , Dawen Liang , Matthew Hoffman

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

Large language models based on the Transformer architecture have demonstrated impressive capabilities to learn in context. However, existing theoretical studies on how this phenomenon arises are limited to the dynamics of a single layer of…

Machine Learning · Statistics 2024-06-04 Juno Kim , Taiji Suzuki

While large training datasets generally offer improvement in model performance, the training process becomes computationally expensive and time consuming. Distributed learning is a common strategy to reduce the overall training time by…

Machine Learning · Statistics 2021-10-22 Nicole Mücke , Enrico Reiss , Jonas Rungenhagen , Markus Klein

Our world is ambiguous and this is reflected in the data we use to train our algorithms. This is particularly true when we try to model natural processes where collected data is affected by noisy measurements and differences in measurement…

Machine Learning · Computer Science 2023-07-19 Jörg K. H. Franke , Frederic Runge , Frank Hutter

Graph neural networks (GNNs) are powerful tools for solving graph-related problems. Distributed GNN frameworks and systems enhance the scalability of GNNs and accelerate model training, yet most are optimized for node classification. Their…

Machine Learning · Computer Science 2025-06-27 Xin Huang , Chul-Ho Lee

In this work, a novel approach for the construction and training of time series models is presented that deals with the problem of learning on large time series with non-equispaced observations, which at the same time may possess features…

Machine Learning · Computer Science 2020-11-25 Charilaos Mylonas , Eleni Chatzi

Natural Language Inference (NLI) models are known to learn from biases and artefacts within their training data, impacting how well they generalise to other unseen datasets. Existing de-biasing approaches focus on preventing the models from…

Computation and Language · Computer Science 2022-05-03 Joe Stacey , Yonatan Belinkov , Marek Rei

Large language models have demonstrated capabilities in text generation, while their increasing parameter scales present challenges in computational and memory efficiency. Post-training sparsity (PTS), which reduces model cost by removing…

Computation and Language · Computer Science 2026-02-26 Minhao Jiang , Zhikai Li , Xuewen Liu , Jing Zhang , Mengjuan Chen , Qingyi Gu

Understanding pragmatics-the use of language in context-is crucial for developing NLP systems capable of interpreting nuanced language use. Despite recent advances in language technologies, including large language models, evaluating their…

Computation and Language · Computer Science 2025-06-13 Bolei Ma , Yuting Li , Wei Zhou , Ziwei Gong , Yang Janet Liu , Katja Jasinskaja , Annemarie Friedrich , Julia Hirschberg , Frauke Kreuter , Barbara Plank

Existing models of network growth typically have one or two parameters or strategies which are fixed for all times. We introduce a general framework where feedback on the current state of a network is used to dynamically alter the values of…

Physics and Society · Physics 2009-01-07 Raissa M. D'Souza , Soumen Roy

We develop a geometric account of sequence modelling that links patterns in the data to measurable properties of the loss landscape in transformer networks. First, we cast conditional sequence distributions into a Hilbert-space framework…

Machine Learning · Computer Science 2025-04-28 Zhongtian Chen , Daniel Murfet

In this paper, we propose a machine learning model, which dynamically changes the features during training. Our main motivation is to update the model in a small content during the training process with replacing less descriptive features…

Machine Learning · Computer Science 2020-02-24 Marcell Beregi-Kovács , Ágnes Baran , András Hajdu
‹ Prev 1 4 5 6 7 8 10 Next ›