State Soup: In-Context Skill Learning, Retrieval and Mixing

• URL: http://arxiv.org/abs/2406.08423v1
• Date: Wed, 12 Jun 2024 17:06:07 GMT
• Title: State Soup: In-Context Skill Learning, Retrieval and Mixing
• Authors: Maciej Pióro, Maciej Wołczyk, Razvan Pascanu, Johannes von Oswald, João Sacramento,
• Abstract summary: A new breed of gated-linear recurrent neural networks has reached state-of-the-art performance on a range of sequence modeling problems. Here, we explore another advantage of these stateful sequence models, inspired by the success of model merging through parameter. Building on parallels between fine-tuning and in-context learning, we investigate whether we can treat internal states as task vectors that can be stored, retrieved, and then linearly combined.
• Score: 22.485700977542127
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: A new breed of gated-linear recurrent neural networks has reached state-of-the-art performance on a range of sequence modeling problems. Such models naturally handle long sequences efficiently, as the cost of processing a new input is independent of sequence length. Here, we explore another advantage of these stateful sequence models, inspired by the success of model merging through parameter interpolation. Building on parallels between fine-tuning and in-context learning, we investigate whether we can treat internal states as task vectors that can be stored, retrieved, and then linearly combined, exploiting the linearity of recurrence. We study this form of fast model merging on Mamba-2.8b, a pretrained recurrent model, and present preliminary evidence that simple linear state interpolation methods suffice to improve next-token perplexity as well as downstream in-context learning task performance.

Related papers

• Joint Diffusion models in Continual Learning [4.013156524547073]
  We introduce JDCL - a new method for continual learning with generative rehearsal based on joint diffusion models. Generative-replay-based continual learning methods try to mitigate this issue by retraining a model with a combination of new and rehearsal data sampled from a generative model. We show that such shared parametrization, combined with the knowledge distillation technique allows for stable adaptation to new tasks without catastrophic forgetting.
  arXiv  Detail & Related papers  (2024-11-12T22:35:44Z)
• Transferable Post-training via Inverse Value Learning [83.75002867411263]
  We propose modeling changes at the logits level during post-training using a separate neural network (i.e., the value network) After training this network on a small base model using demonstrations, this network can be seamlessly integrated with other pre-trained models during inference. We demonstrate that the resulting value network has broad transferability across pre-trained models of different parameter sizes.
  arXiv  Detail & Related papers  (2024-10-28T13:48:43Z)
• AdaMerging: Adaptive Model Merging for Multi-Task Learning [68.75885518081357]
  This paper introduces an innovative technique called Adaptive Model Merging (AdaMerging) It aims to autonomously learn the coefficients for model merging, either in a task-wise or layer-wise manner, without relying on the original training data. Compared to the current state-of-the-art task arithmetic merging scheme, AdaMerging showcases a remarkable 11% improvement in performance.
  arXiv  Detail & Related papers  (2023-10-04T04:26:33Z)
• Tensor Decompositions Meet Control Theory: Learning General Mixtures of Linear Dynamical Systems [19.47235707806519]
  We give a new approach to learning mixtures of linear dynamical systems based on tensor decompositions. Our algorithm succeeds without strong separation conditions on the components, and can be used to compete with the Bayes optimal clustering of the trajectories.
  arXiv  Detail & Related papers  (2023-07-13T03:00:01Z)
• SequenceMatch: Imitation Learning for Autoregressive Sequence Modelling with Backtracking [60.109453252858806]
  A maximum-likelihood (MLE) objective does not match a downstream use-case of autoregressively generating high-quality sequences. We formulate sequence generation as an imitation learning (IL) problem. This allows us to minimize a variety of divergences between the distribution of sequences generated by an autoregressive model and sequences from a dataset. Our resulting method, SequenceMatch, can be implemented without adversarial training or architectural changes.
  arXiv  Detail & Related papers  (2023-06-08T17:59:58Z)
• Learning Sequence Representations by Non-local Recurrent Neural Memory [61.65105481899744]
  We propose a Non-local Recurrent Neural Memory (NRNM) for supervised sequence representation learning. Our model is able to capture long-range dependencies and latent high-level features can be distilled by our model. Our model compares favorably against other state-of-the-art methods specifically designed for each of these sequence applications.
  arXiv  Detail & Related papers  (2022-07-20T07:26:15Z)
• The impact of memory on learning sequence-to-sequence tasks [6.603326895384289]
  Recent success of neural networks in natural language processing has drawn renewed attention to learning sequence-to-sequence (seq2seq) tasks. We propose a model for a seq2seq task that has the advantage of providing explicit control over the degree of memory, or non-Markovianity, in the sequences.
  arXiv  Detail & Related papers  (2022-05-29T14:57:33Z)
• An EM Approach to Non-autoregressive Conditional Sequence Generation [49.11858479436565]
  Autoregressive (AR) models have been the dominating approach to conditional sequence generation. Non-autoregressive (NAR) models have been recently proposed to reduce the latency by generating all output tokens in parallel. This paper proposes a new approach that jointly optimize both AR and NAR models in a unified Expectation-Maximization framework.
  arXiv  Detail & Related papers  (2020-06-29T20:58:57Z)
• Convolutional Tensor-Train LSTM for Spatio-temporal Learning [116.24172387469994]
  We propose a higher-order LSTM model that can efficiently learn long-term correlations in the video sequence. This is accomplished through a novel tensor train module that performs prediction by combining convolutional features across time. Our results achieve state-of-the-art performance-art in a wide range of applications and datasets.
  arXiv  Detail & Related papers  (2020-02-21T05:00:01Z)

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.