Most Likely Sequence Generation for $n$-Grams, Transformers, HMMs, and Markov Chains, by Using Rollout Algorithms

• URL: http://arxiv.org/abs/2403.15465v1
• Date: Tue, 19 Mar 2024 19:58:46 GMT
• Title: Most Likely Sequence Generation for $n$-Grams, Transformers, HMMs, and Markov Chains, by Using Rollout Algorithms
• Authors: Yuchao Li, Dimitri Bertsekas,
• Abstract summary: We consider a transformer with a $n$-gram structure, such as the one underlying ChatGPT. The transformer provides next word probabilities, which can be used to generate word sequences. We consider methods for computing word sequences that are highly likely, based on these probabilities.
• Score: 3.014160809522789
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In this paper we consider a transformer with an $n$-gram structure, such as the one underlying ChatGPT. The transformer provides next word probabilities, which can be used to generate word sequences. We consider methods for computing word sequences that are highly likely, based on these probabilities. Computing the optimal (i.e., most likely) word sequence starting with a given initial state is an intractable problem, so we propose methods to compute highly likely sequences of $N$ words in time that is a low order polynomial in $N$ and in the vocabulary size of the $n$-gram. These methods are based on the rollout approach from approximate dynamic programming, a form of single policy iteration, which can improve the performance of any given heuristic policy. In our case we use a greedy heuristic that generates as next word one that has the highest probability. We show with analysis, examples, and computational experimentation that our methods are capable of generating highly likely sequences with a modest increase in computation over the greedy heuristic. While our analysis and experiments are focused on Markov chains of the type arising in transformer and ChatGPT-like models, our methods apply to general finite-state Markov chains, and related inference applications of Hidden Markov Models (HMM), where Viterbi decoding is used extensively.

Related papers

• QWO: Speeding Up Permutation-Based Causal Discovery in LiGAMs [20.661343069864888]
  We introduce QWO, a novel approach that significantly enhances the efficiency of computing $mathcalGpi$ for a given permutation $pi$. QWO has a speed-up of $O(n2)$ ($n$ is the number of variables) compared to the state-of-the-art BIC-based method, making it highly scalable.
  arXiv  Detail & Related papers  (2024-10-30T16:10:46Z)
• GEC-DePenD: Non-Autoregressive Grammatical Error Correction with Decoupled Permutation and Decoding [52.14832976759585]
  Grammatical error correction (GEC) is an important NLP task that is usually solved with autoregressive sequence-to-sequence models. We propose a novel non-autoregressive approach to GEC that decouples the architecture into a permutation network. We show that the resulting network improves over previously known non-autoregressive methods for GEC.
  arXiv  Detail & Related papers  (2023-11-14T14:24:36Z)
• Learning to Relax: Setting Solver Parameters Across a Sequence of Linear System Instances [42.16343861129583]
  We show that a bandit online learning algorithm can select parameters for a sequence of instances such that the overall cost approaches that of the best fixed $omega$ as the sequence length increases. Our work provides the first learning-theoretic treatment of high-precision linear system solvers and the first end-to-end guarantees for data-driven scientific computing.
  arXiv  Detail & Related papers  (2023-10-03T17:51:42Z)
• Transformers Learn Shortcuts to Automata [52.015990420075944]
  We find that a low-depth Transformer can represent the computations of any finite-state automaton. We show that a Transformer with $O(log T)$ layers can exactly replicate the computation of an automaton on an input sequence of length $T$. We further investigate the brittleness of these solutions and propose potential mitigations.
  arXiv  Detail & Related papers  (2022-10-19T17:45:48Z)
• Efficient and robust high-dimensional sparse logistic regression via nonlinear primal-dual hybrid gradient algorithms [0.0]
  We propose an iterative algorithm that provably computes a solution to a logistic regression problem regularized by an elastic net penalty. This result improves on the known complexity bound of $O(min(m2n,mn2)log (1/epsilon))$ for first-order optimization methods.
  arXiv  Detail & Related papers  (2021-11-30T14:16:48Z)
• Recurrently Predicting Hypergraphs [30.092688729343678]
  A problem arises from the number of possible multi-way relationships, or hyperedges, scaling in $mathcalO(2n)$ for a set of $n$ elements. We propose a recurrent hypergraph neural network that predicts the incidence matrix by iteratively refining an initial guess of the solution.
  arXiv  Detail & Related papers  (2021-06-26T01:12:41Z)
• Clustering Mixture Models in Almost-Linear Time via List-Decodable Mean Estimation [58.24280149662003]
  We study the problem of list-decodable mean estimation, where an adversary can corrupt a majority of the dataset. We develop new algorithms for list-decodable mean estimation, achieving nearly-optimal statistical guarantees.
  arXiv  Detail & Related papers  (2021-06-16T03:34:14Z)
• Determinantal Beam Search [75.84501052642361]
  Beam search is a go-to strategy for decoding neural sequence models. In use-cases that call for multiple solutions, a diverse or representative set is often desired. By posing iterations in beam search as a series of subdeterminant problems, we can turn the algorithm into a diverse subset selection process.
  arXiv  Detail & Related papers  (2021-06-14T13:01:46Z)
• Second-Order Information in Non-Convex Stochastic Optimization: Power and Limitations [54.42518331209581]
  We find an algorithm which finds. epsilon$-approximate stationary point (with $|nabla F(x)|le epsilon$) using. $(epsilon,gamma)$surimate random random points. Our lower bounds here are novel even in the noiseless case.
  arXiv  Detail & Related papers  (2020-06-24T04:41:43Z)
• $O(n)$ Connections are Expressive Enough: Universal Approximability of Sparse Transformers [71.31712741938837]
  We show that sparse Transformers with only $O(n)$ connections per attention layer can approximate the same function class as the dense model with $n2$ connections. We also present experiments comparing different patterns/levels of sparsity on standard NLP tasks.
  arXiv  Detail & Related papers  (2020-06-08T18:30:12Z)

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.