Lattice Representation Learning

• URL: http://arxiv.org/abs/2006.13833v1
• Date: Wed, 24 Jun 2020 16:05:11 GMT
• Title: Lattice Representation Learning
• Authors: Luis A. Lastras
• Abstract summary: We introduce theory and algorithms for learning discrete representations that take on a lattice that is embedded in an Euclidean space. Lattice representations possess an interesting combination of properties: a) they can be computed explicitly using lattice quantization, yet they can be learned efficiently using the ideas we introduce. This article will focus on laying the groundwork for exploring and exploiting the first two properties, including a new mathematical result linking expressions used during training and inference time and experimental validation on two popular datasets.
• Score: 6.427169570069738
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In this article we introduce theory and algorithms for learning discrete representations that take on a lattice that is embedded in an Euclidean space. Lattice representations possess an interesting combination of properties: a) they can be computed explicitly using lattice quantization, yet they can be learned efficiently using the ideas we introduce in this paper, b) they are highly related to Gaussian Variational Autoencoders, allowing designers familiar with the latter to easily produce discrete representations from their models and c) since lattices satisfy the axioms of a group, their adoption can lead into a way of learning simple algebras for modeling binary operations between objects through symbolic formalisms, yet learn these structures also formally using differentiation techniques. This article will focus on laying the groundwork for exploring and exploiting the first two properties, including a new mathematical result linking expressions used during training and inference time and experimental validation on two popular datasets.

Related papers

• Acceleration of Grokking in Learning Arithmetic Operations via Kolmogorov-Arnold Representation [3.7812707887425048]
  We focus on the grokking phenomenon that arises in learning arithmetic binary operations via the transformer model. We suggest various transfer learning mechanisms that expedite grokking.
  arXiv  Detail & Related papers  (2024-05-26T18:29:24Z)
• On the Origins of Linear Representations in Large Language Models [51.88404605700344]
  We introduce a simple latent variable model to formalize the concept dynamics of the next token prediction. Experiments show that linear representations emerge when learning from data matching the latent variable model. We additionally confirm some predictions of the theory using the LLaMA-2 large language model.
  arXiv  Detail & Related papers  (2024-03-06T17:17:36Z)
• Discovering Abstract Symbolic Relations by Learning Unitary Group Representations [7.303827428956944]
  We investigate a principled approach for symbolic operation completion (SOC) SOC poses a unique challenge in modeling abstract relationships between discrete symbols. We demonstrate that SOC can be efficiently solved by a minimal model - a bilinear map - with a novel factorized architecture.
  arXiv  Detail & Related papers  (2024-02-26T20:18:43Z)
• Object-centric architectures enable efficient causal representation learning [51.6196391784561]
  We show that when the observations are of multiple objects, the generative function is no longer injective and disentanglement fails in practice. We develop an object-centric architecture that leverages weak supervision from sparse perturbations to disentangle each object's properties. This approach is more data-efficient in the sense that it requires significantly fewer perturbations than a comparable approach that encodes to a Euclidean space.
  arXiv  Detail & Related papers  (2023-10-29T16:01:03Z)
• Discovering interpretable elastoplasticity models via the neural polynomial method enabled symbolic regressions [0.0]
  Conventional neural network elastoplasticity models are often perceived as lacking interpretability. This paper introduces a two-step machine learning approach that returns mathematical models interpretable by human experts.
  arXiv  Detail & Related papers  (2023-07-24T22:22:32Z)
• A Recursive Bateson-Inspired Model for the Generation of Semantic Formal Concepts from Spatial Sensory Data [77.34726150561087]
  This paper presents a new symbolic-only method for the generation of hierarchical concept structures from complex sensory data. The approach is based on Bateson's notion of difference as the key to the genesis of an idea or a concept. The model is able to produce fairly rich yet human-readable conceptual representations without training.
  arXiv  Detail & Related papers  (2023-07-16T15:59:13Z)
• Linear Spaces of Meanings: Compositional Structures in Vision-Language Models [110.00434385712786]
  We investigate compositional structures in data embeddings from pre-trained vision-language models (VLMs) We first present a framework for understanding compositional structures from a geometric perspective. We then explain what these structures entail probabilistically in the case of VLM embeddings, providing intuitions for why they arise in practice.
  arXiv  Detail & Related papers  (2023-02-28T08:11:56Z)
• Equivariance with Learned Canonicalization Functions [77.32483958400282]
  We show that learning a small neural network to perform canonicalization is better than using predefineds. Our experiments show that learning the canonicalization function is competitive with existing techniques for learning equivariant functions across many tasks.
  arXiv  Detail & Related papers  (2022-11-11T21:58:15Z)
• Granular Directed Rough Sets, Concept Organization and Soft Clustering [0.0]
  Up-directed rough sets are introduced and studied by the present author in earlier papers. This is extended by her in two different granular directions, with a surprising algebraic semantics. This research is expected to see significant theoretical and practical applications in related domains.
  arXiv  Detail & Related papers  (2022-08-13T11:01:05Z)
• Object Representations as Fixed Points: Training Iterative Refinement Algorithms with Implicit Differentiation [88.14365009076907]
  Iterative refinement is a useful paradigm for representation learning. We develop an implicit differentiation approach that improves the stability and tractability of training.
  arXiv  Detail & Related papers  (2022-07-02T10:00:35Z)

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.