Abrupt Learning in Transformers: A Case Study on Matrix Completion

• URL: http://arxiv.org/abs/2410.22244v1
• Date: Tue, 29 Oct 2024 17:08:06 GMT
• Title: Abrupt Learning in Transformers: A Case Study on Matrix Completion
• Authors: Pulkit Gopalani, Ekdeep Singh Lubana, Wei Hu,
• Abstract summary: We formulate the low-rank matrix completion problem as a masked language modeling (MLM) task. We show that it is possible to train a BERT model to solve this task to low error. We also analyze the training dynamics of individual model components to understand the sudden drop in loss.
• Score: 15.210510215283882
• License:
• Abstract: Recent analysis on the training dynamics of Transformers has unveiled an interesting characteristic: the training loss plateaus for a significant number of training steps, and then suddenly (and sharply) drops to near--optimal values. To understand this phenomenon in depth, we formulate the low-rank matrix completion problem as a masked language modeling (MLM) task, and show that it is possible to train a BERT model to solve this task to low error. Furthermore, the loss curve shows a plateau early in training followed by a sudden drop to near-optimal values, despite no changes in the training procedure or hyper-parameters. To gain interpretability insights into this sudden drop, we examine the model's predictions, attention heads, and hidden states before and after this transition. Concretely, we observe that (a) the model transitions from simply copying the masked input to accurately predicting the masked entries; (b) the attention heads transition to interpretable patterns relevant to the task; and (c) the embeddings and hidden states encode information relevant to the problem. We also analyze the training dynamics of individual model components to understand the sudden drop in loss.

Related papers

• Training Dynamics of Transformers to Recognize Word Co-occurrence via Gradient Flow Analysis [97.54180451650122]
  We study the dynamics of training a shallow transformer on a task of recognizing co-occurrence of two designated words. We analyze the gradient flow dynamics of simultaneously training three attention matrices and a linear layer. We prove a novel property of the gradient flow, termed textitautomatic balancing of gradients, which enables the loss values of different samples to decrease almost at the same rate and further facilitates the proof of near minimum training loss.
  arXiv  Detail & Related papers  (2024-10-12T17:50:58Z)
• Parameter-Efficient and Memory-Efficient Tuning for Vision Transformer: A Disentangled Approach [87.8330887605381]
  We show how to adapt a pre-trained Vision Transformer to downstream recognition tasks with only a few learnable parameters. We synthesize a task-specific query with a learnable and lightweight module, which is independent of the pre-trained model. Our method achieves state-of-the-art performance under memory constraints, showcasing its applicability in real-world situations.
  arXiv  Detail & Related papers  (2024-07-09T15:45:04Z)
• In-Context Convergence of Transformers [63.04956160537308]
  We study the learning dynamics of a one-layer transformer with softmax attention trained via gradient descent. For data with imbalanced features, we show that the learning dynamics take a stage-wise convergence process.
  arXiv  Detail & Related papers  (2023-10-08T17:55:33Z)
• Uncovering mesa-optimization algorithms in Transformers [61.06055590704677]
  Some autoregressive models can learn as an input sequence is processed, without undergoing any parameter changes, and without being explicitly trained to do so. We show that standard next-token prediction error minimization gives rise to a subsidiary learning algorithm that adjusts the model as new inputs are revealed. Our findings explain in-context learning as a product of autoregressive loss minimization and inform the design of new optimization-based Transformer layers.
  arXiv  Detail & Related papers  (2023-09-11T22:42:50Z)
• What Happens During Finetuning of Vision Transformers: An Invariance Based Investigation [7.432224771219168]
  The pretrain-finetune paradigm usually improves downstream performance over training a model from scratch on the same task. In this work, we examine the relationship between pretrained vision transformers and the corresponding finetuned versions on several benchmark datasets and tasks.
  arXiv  Detail & Related papers  (2023-07-12T08:35:24Z)
• Trained Transformers Learn Linear Models In-Context [39.56636898650966]
  Attention-based neural networks as transformers have demonstrated a remarkable ability to exhibit inattention learning (ICL) We show that when transformer training over random instances of linear regression problems, these models' predictions mimic nonlinear of ordinary squares.
  arXiv  Detail & Related papers  (2023-06-16T15:50:03Z)
• Inverse Scaling: When Bigger Isn't Better [80.42834197416444]
  Large language models (LMs) show predictable improvements to overall loss with increased scale. We present evidence for the claim that LMs may show inverse scaling, or worse task performance with increased scale.
  arXiv  Detail & Related papers  (2023-06-15T20:11:23Z)
• Hard Patches Mining for Masked Image Modeling [52.46714618641274]
  Masked image modeling (MIM) has attracted much research attention due to its promising potential for learning scalable visual representations. We propose Hard Patches Mining (HPM), a brand-new framework for MIM pre-training.
  arXiv  Detail & Related papers  (2023-04-12T15:38:23Z)
• On the Effect of Pre-training for Transformer in Different Modality on Offline Reinforcement Learning [0.0]
  We investigate how pre-training on data of different modalities, such as language and vision, affects fine-tuning of Transformer-based models to Mujoco offline reinforcement learning tasks.
  arXiv  Detail & Related papers  (2022-11-17T13:34:08Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.