DISCO : efficient unsupervised decoding for discrete natural language problems via convex relaxation

• URL: http://arxiv.org/abs/2107.05380v2
• Date: Tue, 13 Jul 2021 20:34:37 GMT
• Title: DISCO : efficient unsupervised decoding for discrete natural language problems via convex relaxation
• Authors: Anish Acharya, Rudrajit Das
• Abstract summary: We study test time decoding; an ubiquitous step in almost all sequential text generation task spanning across a wide array of natural language processing (NLP) problems. Our main contribution is to develop a continuous relaxation framework for the NP-hard decoding problem and propose Disco - an efficient algorithm based on standard first order gradient based.
• Score: 1.370633147306388
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: In this paper we study test time decoding; an ubiquitous step in almost all sequential text generation task spanning across a wide array of natural language processing (NLP) problems. Our main contribution is to develop a continuous relaxation framework for the combinatorial NP-hard decoding problem and propose Disco - an efficient algorithm based on standard first order gradient based. We provide tight analysis and show that our proposed algorithm linearly converges to within $\epsilon$ neighborhood of the optima. Finally, we perform preliminary experiments on the task of adversarial text generation and show superior performance of Disco over several popular decoding approaches.

Related papers

• Faster WIND: Accelerating Iterative Best-of-$N$ Distillation for LLM Alignment [81.84950252537618]
  This paper reveals a unified game-theoretic connection between iterative BOND and self-play alignment. We establish a novel framework, WIN rate Dominance (WIND), with a series of efficient algorithms for regularized win rate dominance optimization.
  arXiv  Detail & Related papers  (2024-10-28T04:47:39Z)
• A Three-Stage Algorithm for the Closest String Problem on Artificial and Real Gene Sequences [39.58317527488534]
  Closest String Problem is an NP-hard problem that aims to find a string that has the minimum distance from all sequences that belong to the given set of strings. In this paper, we introduce a three-stage algorithm that comprises the following process: first, we apply a novel alphabet pruning method to reduce the search space for effectively finding promising search regions. Second, a variant of beam search to find a solution is employed. This method utilizes a newly developed guiding function based on an expected distance score of partial solutions.
  arXiv  Detail & Related papers  (2024-07-17T21:26:27Z)
• Optimizing NOTEARS Objectives via Topological Swaps [41.18829644248979]
  In this paper, we develop an effective method for a set of candidate algorithms. At the inner level, given a subject, we utilize off-the-the-art constraints. The proposed method significantly improves the score of other algorithms.
  arXiv  Detail & Related papers  (2023-05-26T21:49:37Z)
• A Sequential Deep Learning Algorithm for Sampled Mixed-integer Optimisation Problems [0.3867363075280544]
  We introduce and analyse two efficient algorithms for mixed-integer optimisation problems. We show that both algorithms exhibit finite-time convergence towards the optimal solution. We establish quantitatively the efficacy of these algorithms by means of three numerical tests.
  arXiv  Detail & Related papers  (2023-01-25T17:10:52Z)
• Best-$k$ Search Algorithm for Neural Text Generation [118.02691398555781]
  We propose a deterministic search algorithm balancing both quality and diversity. The proposed algorithm is parameter-free, lightweight, efficient, and easy to use.
  arXiv  Detail & Related papers  (2022-11-22T00:26:13Z)
• An Asymptotically Optimal Primal-Dual Incremental Algorithm for Contextual Linear Bandits [129.1029690825929]
  We introduce a novel algorithm improving over the state-of-the-art along multiple dimensions. We establish minimax optimality for any learning horizon in the special case of non-contextual linear bandits.
  arXiv  Detail & Related papers  (2020-10-23T09:12:47Z)
• Adaptive Sampling for Best Policy Identification in Markov Decision Processes [79.4957965474334]
  We investigate the problem of best-policy identification in discounted Markov Decision (MDPs) when the learner has access to a generative model. The advantages of state-of-the-art algorithms are discussed and illustrated.
  arXiv  Detail & Related papers  (2020-09-28T15:22:24Z)
• Accelerated Message Passing for Entropy-Regularized MAP Inference [89.15658822319928]
  Maximum a posteriori (MAP) inference in discrete-valued random fields is a fundamental problem in machine learning. Due to the difficulty of this problem, linear programming (LP) relaxations are commonly used to derive specialized message passing algorithms. We present randomized methods for accelerating these algorithms by leveraging techniques that underlie classical accelerated gradient.
  arXiv  Detail & Related papers  (2020-07-01T18:43:32Z)
• Optimal Randomized First-Order Methods for Least-Squares Problems [56.05635751529922]
  This class of algorithms encompasses several randomized methods among the fastest solvers for least-squares problems. We focus on two classical embeddings, namely, Gaussian projections and subsampled Hadamard transforms. Our resulting algorithm yields the best complexity known for solving least-squares problems with no condition number dependence.
  arXiv  Detail & Related papers  (2020-02-21T17:45:32Z)

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.