From Attention to Atoms: Spectral Dictionary Learning for Fast, Interpretable Language Models

• URL: http://arxiv.org/abs/2505.00033v1
• Date: Tue, 29 Apr 2025 13:24:42 GMT
• Title: From Attention to Atoms: Spectral Dictionary Learning for Fast, Interpretable Language Models
• Authors: Andrew Kiruluta,
• Abstract summary: We propose a novel spectral generative modeling framework for natural language processing that jointly learns a global time varying Fourier dictionary and per token mixing coefficients.<n>Our approach achieves competitive perplexity and generation quality on standard benchmarks such as WikiText2 and Penn Treebank.<n>We demonstrate that spectral dictionary models can achieve competitive performance compared to transformer baselines while significantly reducing inference latency and memory footprint.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We propose a novel spectral generative modeling framework for natural language processing that jointly learns a global time varying Fourier dictionary and per token mixing coefficients, replacing the ubiquitous self attention mechanism in transformer architectures. By enforcing reconstruction losses in both the time domain (embedding reconstruction) and the frequency domain (via Short Time Fourier Transform magnitude matching) alongside a standard language modeling objective, and fitting a Gaussian Mixture Model (GMM) prior over the learned mixing vectors, our approach achieves competitive perplexity and generation quality on standard benchmarks such as WikiText2 and Penn Treebank. In contrast to the quadratic computation complexity of self attention, our method operates with linear complexity, delivering substantial efficiency gains. We demonstrate that spectral dictionary models can achieve competitive performance compared to transformer baselines while significantly reducing inference latency and memory footprint, offering a compelling alternative for scalable language modeling.

Related papers

• Polynomial Mixing for Efficient Self-supervised Speech Encoders [50.58463928808225]
  Polynomial Mixer (PoM) is a drop-in replacement for multi-head self-attention.<n>PoM achieves its performance on downstream speech recognition tasks.
  arXiv  Detail & Related papers  (2026-02-28T14:45:55Z)
• Learnable Multi-Scale Wavelet Transformer: A Novel Alternative to Self-Attention [0.0]
  Learnable Multi-Scale Wavelet Transformer (LMWT) is a novel architecture that replaces the standard dot-product self-attention.<n>We present the detailed mathematical formulation of the learnable Haar wavelet module and its integration into the transformer framework.<n>Our results indicate that the LMWT achieves competitive performance while offering substantial computational advantages.
  arXiv  Detail & Related papers  (2025-04-08T22:16:54Z)
• State Fourier Diffusion Language Model (SFDLM): A Scalable, Novel Iterative Approach to Language Modeling [0.0]
  This paper introduces a fully diffusion driven discrete text generation model built without any transformer or large convolution modules.<n>By composing local state space updates with global Fourier based mixing, the approach effectively captures both short and long range dependencies.
  arXiv  Detail & Related papers  (2025-03-16T02:17:40Z)
• Latent Thought Models with Variational Bayes Inference-Time Computation [52.63299874322121]
  Latent Thought Models (LTMs) incorporate explicit latent thought vectors that follow an explicit prior model in latent space.<n>LTMs demonstrate superior sample and parameter efficiency compared to autoregressive models and discrete diffusion models.
  arXiv  Detail & Related papers  (2025-02-03T17:50:34Z)
• Enhancing Foundation Models for Time Series Forecasting via Wavelet-based Tokenization [74.3339999119713]
  We develop a wavelet-based tokenizer that allows models to learn complex representations directly in the space of time-localized frequencies. Our method first scales and decomposes the input time series, then thresholds and quantizes the wavelet coefficients, and finally pre-trains an autoregressive model to forecast coefficients for the forecast horizon.
  arXiv  Detail & Related papers  (2024-12-06T18:22:59Z)
• Real-World Compositional Generalization with Disentangled Sequence-to-Sequence Learning [81.24269148865555]
  A recently proposed Disentangled sequence-to-sequence model (Dangle) shows promising generalization capability. We introduce two key modifications to this model which encourage more disentangled representations and improve its compute and memory efficiency. Specifically, instead of adaptively re-encoding source keys and values at each time step, we disentangle their representations and only re-encode keys periodically.
  arXiv  Detail & Related papers  (2022-12-12T15:40:30Z)
• Bayesian Prompt Learning for Image-Language Model Generalization [64.50204877434878]
  We use the regularization ability of Bayesian methods to frame prompt learning as a variational inference problem. Our approach regularizes the prompt space, reduces overfitting to the seen prompts and improves the prompt generalization on unseen prompts. We demonstrate empirically on 15 benchmarks that Bayesian prompt learning provides an appropriate coverage of the prompt space.
  arXiv  Detail & Related papers  (2022-10-05T17:05:56Z)
• Pre-Training a Graph Recurrent Network for Language Representation [34.4554387894105]
  We consider a graph recurrent network for language model pre-training, which builds a graph structure for each sequence with local token-level communications. We find that our model can generate more diverse outputs with less contextualized feature redundancy than existing attention-based models.
  arXiv  Detail & Related papers  (2022-09-08T14:12:15Z)
• Global Filter Networks for Image Classification [90.81352483076323]
  We present a conceptually simple yet computationally efficient architecture that learns long-term spatial dependencies in the frequency domain with log-linear complexity. Our results demonstrate that GFNet can be a very competitive alternative to transformer-style models and CNNs in efficiency, generalization ability and robustness.
  arXiv  Detail & Related papers  (2021-07-01T17:58:16Z)
• GroupBERT: Enhanced Transformer Architecture with Efficient Grouped Structures [57.46093180685175]
  We demonstrate a set of modifications to the structure of a Transformer layer, producing a more efficient architecture. We add a convolutional module to complement the self-attention module, decoupling the learning of local and global interactions. We apply the resulting architecture to language representation learning and demonstrate its superior performance compared to BERT models of different scales.
  arXiv  Detail & Related papers  (2021-06-10T15:41:53Z)
• Revisiting Simple Neural Probabilistic Language Models [27.957834093475686]
  This paper revisits the neural probabilistic language model (NPLM) ofcitetBengio2003ANP. When scaled up to modern hardware, this model performs much better than expected on word-level language model benchmarks. Inspired by this result, we modify the Transformer by replacing its first self-attention layer with the NPLM's local concatenation layer.
  arXiv  Detail & Related papers  (2021-04-08T02:18:47Z)
• Early Stage LM Integration Using Local and Global Log-Linear Combination [46.91755970827846]
  Sequence-to-sequence models with an implicit alignment mechanism (e.g. attention) are closing the performance gap towards traditional hybrid hidden Markov models (HMM) One important factor to improve word error rate in both cases is the use of an external language model (LM) trained on large text-only corpora. We present a novel method for language model integration into implicit-alignment based sequence-to-sequence models.
  arXiv  Detail & Related papers  (2020-05-20T13:49:55Z)
• Improve Variational Autoencoder for Text Generationwith Discrete Latent Bottleneck [52.08901549360262]
  Variational autoencoders (VAEs) are essential tools in end-to-end representation learning. VAEs tend to ignore latent variables with a strong auto-regressive decoder. We propose a principled approach to enforce an implicit latent feature matching in a more compact latent space.
  arXiv  Detail & Related papers  (2020-04-22T14:41:37Z)

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.