Birdie: Advancing State Space Models with Reward-Driven Objectives and Curricula

• URL: http://arxiv.org/abs/2411.01030v3
• Date: Thu, 07 Nov 2024 00:23:14 GMT
• Title: Birdie: Advancing State Space Models with Reward-Driven Objectives and Curricula
• Authors: Sam Blouir, Jimmy T. H. Smith, Antonios Anastasopoulos, Amarda Shehu,
• Abstract summary: State space models (SSMs) offer advantages over Transformers but struggle with tasks requiring long-range in-context retrieval-like text copying, associative recall, and question answering over long contexts. We propose a novel training procedure, Birdie, that significantly enhances the in-context retrieval capabilities of SSMs without altering their architecture.
• Score: 23.071384759427072
• License:
• Abstract: Efficient state space models (SSMs), such as linear recurrent neural networks and linear attention variants, offer computational advantages over Transformers but struggle with tasks requiring long-range in-context retrieval-like text copying, associative recall, and question answering over long contexts. Previous efforts to address these challenges have focused on architectural modifications, often reintroducing computational inefficiencies. In this paper, we propose a novel training procedure, Birdie, that significantly enhances the in-context retrieval capabilities of SSMs without altering their architecture. Our approach combines bidirectional input processing with dynamic mixtures of specialized pre-training objectives, optimized via reinforcement learning. We introduce a new bidirectional SSM architecture that seamlessly transitions from bidirectional context processing to causal generation. Experimental evaluations demonstrate that Birdie markedly improves performance on retrieval-intensive tasks such as multi-number phone book lookup, long paragraph question-answering, and infilling. This narrows the performance gap with Transformers, while retaining computational efficiency. Our findings highlight the importance of training procedures in leveraging the fixed-state capacity of SSMs, offering a new direction to advance their capabilities. All code and pre-trained models are available at https://www.github.com/samblouir/birdie, with support for JAX and PyTorch.

Related papers

• Taipan: Efficient and Expressive State Space Language Models with Selective Attention [100.16383527459429]
  Long-context language modeling is a significant challenge in Natural Language Processing (NLP) Recent State Space Models (SSMs) such as Mamba offer alternatives with constant memory usage, but they underperform in tasks requiring extensive in-context retrieval. We introduce Taipan, a novel hybrid architecture that combines Mamba-2 with Selective Attention Layers (SALs) Our experiments demonstrate Taipan's superior performance across various scales and tasks, offering a promising solution for efficient long-context language modeling.
  arXiv  Detail & Related papers  (2024-10-24T09:25:37Z)
• RecurFormer: Not All Transformer Heads Need Self-Attention [14.331807060659902]
  Transformer-based large language models (LLMs) excel in modeling complex language patterns but face significant computational costs during inference. We propose RecurFormer, a novel architecture that replaces certain attention heads with linear recurrent neural networks.
  arXiv  Detail & Related papers  (2024-10-10T15:24:12Z)
• SHERL: Synthesizing High Accuracy and Efficient Memory for Resource-Limited Transfer Learning [63.93193829913252]
  We propose an innovative METL strategy called SHERL for resource-limited scenarios. In the early route, intermediate outputs are consolidated via an anti-redundancy operation. In the late route, utilizing minimal late pre-trained layers could alleviate the peak demand on memory overhead.
  arXiv  Detail & Related papers  (2024-07-10T10:22:35Z)
• Sparser is Faster and Less is More: Efficient Sparse Attention for Long-Range Transformers [58.5711048151424]
  We introduce SPARSEK Attention, a novel sparse attention mechanism designed to overcome computational and memory obstacles. Our approach integrates a scoring network and a differentiable top-k mask operator, SPARSEK, to select a constant number of KV pairs for each query. Experimental results reveal that SPARSEK Attention outperforms previous sparse attention methods.
  arXiv  Detail & Related papers  (2024-06-24T15:55:59Z)
• RankMamba: Benchmarking Mamba's Document Ranking Performance in the Era of Transformers [2.8554857235549753]
  Transformer architecture's core mechanism -- attention requires $O(n2)$ time complexity in training and $O(n)$ time complexity in inference. A notable model structure -- Mamba, which is based on state space models, has achieved transformer-equivalent performance in sequence modeling tasks. We find that Mamba models achieve competitive performance compared to transformer-based models with the same training recipe.
  arXiv  Detail & Related papers  (2024-03-27T06:07:05Z)
• Supervised Pretraining Can Learn In-Context Reinforcement Learning [96.62869749926415]
  In this paper, we study the in-context learning capabilities of transformers in decision-making problems. We introduce and study Decision-Pretrained Transformer (DPT), a supervised pretraining method where the transformer predicts an optimal action. We find that the pretrained transformer can be used to solve a range of RL problems in-context, exhibiting both exploration online and conservatism offline.
  arXiv  Detail & Related papers  (2023-06-26T17:58:50Z)
• MASTER: Multi-task Pre-trained Bottlenecked Masked Autoencoders are Better Dense Retrievers [140.0479479231558]
  In this work, we aim to unify a variety of pre-training tasks into a multi-task pre-trained model, namely MASTER. MASTER utilizes a shared-encoder multi-decoder architecture that can construct a representation bottleneck to compress the abundant semantic information across tasks into dense vectors.
  arXiv  Detail & Related papers  (2022-12-15T13:57:07Z)
• Efficient Retrieval Optimized Multi-task Learning [16.189136169520424]
  We propose a novel Retrieval Optimized Multi-task (ROM) framework for jointly training self-supervised tasks, knowledge retrieval, and extractive question answering. Our ROM approach presents a unified and generalizable framework that enables scaling efficiently to multiple tasks. Using our framework, we achieve comparable or better performance than recent methods on QA, while drastically reducing the number of parameters.
  arXiv  Detail & Related papers  (2021-04-20T17:16:34Z)
• Unsupervised Transfer Learning for Spatiotemporal Predictive Networks [90.67309545798224]
  We study how to transfer knowledge from a zoo of unsupervisedly learned models towards another network. Our motivation is that models are expected to understand complex dynamics from different sources. Our approach yields significant improvements on three benchmarks fortemporal prediction, and benefits the target even from less relevant ones.
  arXiv  Detail & Related papers  (2020-09-24T15:40:55Z)

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.