English
Related papers

Related papers: B2T Connection: Serving Stability and Performance …

200 papers

This paper explores the novel deep learning Transformers architectures for high-frequency Bitcoin-USDT log-return forecasting and compares them to the traditional Long Short-Term Memory models. A hybrid Transformer model, called…

Statistical Finance · Quantitative Finance 2023-02-28 Fazl Barez , Paul Bilokon , Arthur Gervais , Nikita Lisitsyn

Quantization-aware training (QAT) is essential for deploying large models under strict memory and latency constraints, yet achieving stable and robust optimization at ultra-low bitwidths remains challenging. Common approaches based on the…

Machine Learning · Computer Science 2026-02-19 Tianyi Chen , Sihan Chen , Xiaoyi Qu , Dan Zhao , Ruomei Yan , Jongwoo Ko , Luming Liang , Pashmina Cameron

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…

Machine Learning · Computer Science 2020-02-19 Nikita Kitaev , Łukasz Kaiser , Anselm Levskaya

Deep neural network training involves both forward propagation (from features through logits to loss) and backward propagation (from loss through gradients to parameter updates). While perturbations along the forward chain, including…

Machine Learning · Computer Science 2026-05-29 Hua Li

Reinforcement Learning (RL) for training Large Language Models is notoriously unstable. While recent studies attribute this to "training inference mismatch stemming" from inconsistent hybrid engines, standard remedies, such as Importance…

Machine Learning · Computer Science 2026-02-03 Yaxiang Zhang , Yingru Li , Jiacai Liu , Jiawei Xu , Ziniu Li , Qian Liu , Haoyuan Li

We introduce a new technique for gradient normalization during neural network training. The gradients are rescaled during the backward pass using normalization layers introduced at certain points within the network architecture. These…

Machine Learning · Computer Science 2021-06-18 Alejandro Cabana , Luis F. Lago-Fernández

Finetuning pretrained models occurs in a low-dimensional subspace of the full parameter space. Prior work has focused on characterizing this optimization subspace, but largely ignored the complementary question: why do certain directions…

Machine Learning · Computer Science 2026-05-11 Junjie Yu , Yue Wang , Zihan Deng , Yan Zhu , Wenxiao Ma , Quanying Liu

The LayerNorm (LN) layer in GPT-style transformer models has long been a hindrance to mechanistic interpretability. LN is a crucial component required to stabilize the training of large language models, and LN or the similar RMSNorm have…

Computation and Language · Computer Science 2024-11-19 Stefan Heimersheim

Multilayer transformer networks consist of interleaved self-attention and feedforward sublayers. Could ordering the sublayers in a different pattern lead to better performance? We generate randomly ordered transformers and train them with…

Computation and Language · Computer Science 2020-04-24 Ofir Press , Noah A. Smith , Omer Levy

Modern large language models (LLMs) excel at tasks that require storing and retrieving knowledge, such as factual recall and question answering. Transformers are central to this capability because they can encode information during training…

Machine Learning · Statistics 2026-03-18 Nuri Mert Vural , Alberto Bietti , Mahdi Soltanolkotabi , Denny Wu

In the pursuit of reducing the number of trainable parameters in deep transformer networks, we employ Reinforcement Learning to dynamically select layers during training and tie them together. Every few iterations, the RL agent is asked…

Machine Learning · Computer Science 2024-01-24 Tamir David Hay , Lior Wolf

Transformers, the standard implementation for large language models (LLMs), typically consist of tens to hundreds of discrete layers. While more layers can lead to better performance, this approach has been challenged as far from efficient,…

Machine Learning · Computer Science 2025-05-21 Yen-Chen Wu , Feng-Ting Liao , Meng-Hsi Chen , Pei-Chen Ho , Farhang Nabiei , Da-shan Shiu

Layer-wise normalization (LN) is an essential component of virtually all transformer-based large language models. While its effects on training stability are well documented, its role at inference time is poorly understood. Additionally, LN…

Machine Learning · Computer Science 2025-07-04 Luca Baroni , Galvin Khara , Joachim Schaeffer , Marat Subkhankulov , Stefan Heimersheim

There remain many open questions pertaining to the scaling behaviour of Transformer architectures. These scaling decisions and findings can be critical, as training runs often come with an associated computational cost which have both…

Computation and Language · Computer Science 2022-02-01 Yi Tay , Mostafa Dehghani , Jinfeng Rao , William Fedus , Samira Abnar , Hyung Won Chung , Sharan Narang , Dani Yogatama , Ashish Vaswani , Donald Metzler

Modeling the parser state is key to good performance in transition-based parsing. Recurrent Neural Networks considerably improved the performance of transition-based systems by modelling the global state, e.g. stack-LSTM parsers, or local…

Computation and Language · Computer Science 2020-10-22 Ramon Fernandez Astudillo , Miguel Ballesteros , Tahira Naseem , Austin Blodgett , Radu Florian

Recent works have indicated redundancy across transformer blocks, prompting the research of depth compression to prune less crucial blocks. However, current ways of entire-block pruning suffer from risks of discarding meaningful cues…

Computer Vision and Pattern Recognition · Computer Science 2026-02-10 Ruihan Xu , Qingpei Guo , Yao Zhu , Xiangyang Ji , Ming Yang , Shiliang Zhang

Training convolutional neural networks (CNNs) with a strict 1-Lipschitz constraint under the $l_{2}$ norm is useful for adversarial robustness, interpretable gradients and stable training. 1-Lipschitz CNNs are usually designed by enforcing…

Machine Learning · Computer Science 2022-11-17 Sahil Singla , Soheil Feizi

Despite advancements in splicing detection, practitioners still struggle to fully leverage forensic tools from the literature due to a critical issue: deep learning-based detectors are extremely sensitive to their trained instances. Simple…

Signal Processing · Electrical Eng. & Systems 2024-09-09 Julien Simon de Kergunic , Rony Abecidan , Patrick Bas , Vincent Itier

Transformer layers, which use an alternating pattern of multi-head attention and multi-layer perceptron (MLP) layers, provide an effective tool for a variety of machine learning problems. As the transformer layers use residual connections…

Machine Learning · Computer Science 2022-12-13 Yaofeng Desmond Zhong , Tongtao Zhang , Amit Chakraborty , Biswadip Dey

Learning rate configuration is a fundamental aspect of modern deep learning. The prevailing practice of applying a uniform learning rate across all layers overlooks the structural heterogeneity of Transformers, potentially limiting their…

Machine Learning · Computer Science 2026-05-28 Di He , Songjun Tu , Keyu Wang , Lu Yin , Shiwei Liu