arXiv research

P3BO optimizes biological sequence design by combining multiple methods.

Deep learning models optimize protein sequences.

OptiGAN uses GAN and RL to optimize sequence generation for specific goals.

Understanding optimal prompts for binary sequence predictors is challenging.

Unified approach for sequence design combining likelihood-free inference and black-box optimization.

LES optimizes designs by sampling descent sequences, achieving strong sample efficiency.

We present Optimal Completion Distillation (OCD), a training procedure for optimizing sequence to sequence models based on edit distance. OCD is efficient, has no hyper-parameters of its own, and does not require pretraining or joint optimization with conditional log-likelihood. Given a partial sequence generated by th…

Neural network optimizes learning sequence for reading words.

Deep RL optimizes compiler passes for better performance.

A faster method for optimizing DNA and protein sequences using machine learning.

Given a sequential learning algorithm and a target model, sequential machine teaching aims to find the shortest training sequence to drive the learning algorithm to the target model. We present the first principled way to find such shortest training sequences. Our key insight is to formulate sequential machine teaching…

LaMBO optimizes biological sequences using autoencoders and Bayesian optimization.

A new framework improves ASR alignment accuracy via optimal transport.

BoGA combines evolutionary search with Bayesian optimization for efficient protein design.

Proposes a continuous relaxation for discrete Bayesian optimization.

Sequence-to-Sequence (seq2seq) modeling has rapidly become an important general-purpose NLP tool that has proven effective for many text-generation and sequence-labeling tasks. Seq2seq builds on deep neural language modeling and inherits its remarkable accuracy in estimating local, next-word distributions. In this work…

Paper optimizes change-point detection using learned distributions from training sequences.

This paper uses bandit theory and Thompson Sampling to optimize protein sequences.

A new method optimizes neural sequence models for better task performance.

Bayesian optimization of antibodies learns from immune system evolution.

Paper uses transfer learning and Bayesian optimization to reduce DNA sequence design experiments.

Hard visual attention is a promising approach to reduce the computational burden of modern computer vision methodologies. Hard attention mechanisms are typically non-differentiable. They can be trained with reinforcement learning but the high-variance training this entails hinders more widespread application. We show h…

Optimal Farey sequence for $Γ_0(2^n)$ with upper bound $2^{n-1}$.

AntBO optimizes antibody design using Bayesian optimization for efficient and effective CDRH3 sequence generation.

Hybridizes CEM and gradient descent for efficient model-predictive control.

Near-optimal confidence intervals for bounded data.

RTRL optimizes long sequences without truncation, converging to loss minima.

For any prime power $q$ and any dimension $s \ge 1$, we present a construction of $(t,s)$-sequences in base $q$ with finite-row generating matrices such that, for fixed $q$, the quality parameter $t$ is asymptotically optimal as a function of $s$ as $s \to \infty$. This is the first construction of $(t,s)$-sequences th…

In this paper, we propose a deep learning approach to tackle the automatic summarization tasks by incorporating topic information into the convolutional sequence-to-sequence (ConvS2S) model and using self-critical sequence training (SCST) for optimization. Through jointly attending to topics and word-level alignment, o…

In sequence generation task, many works use policy gradient for model optimization to tackle the intractable backpropagation issue when maximizing the non-differentiable evaluation metrics or fooling the discriminator in adversarial learning. In this paper, we replace policy gradient with proximal policy optimization (…

Optimizes sliding window approach for tracking Gaussian densities.

This article explores the concepts of ocean wave multivariate multistep forecasting, reconstruction and feature selection. We introduce recurrent neural network frameworks, integrated with Bayesian hyperparameter optimization and Elastic Net methods. We consider both short- and long-term forecasts and reconstruction, f…

Existing imitation learning approaches often require that the complete demonstration data, including sequences of actions and states, are available. In this paper, we consider a more realistic and difficult scenario where a reinforcement learning agent only has access to the state sequences of an expert, while the expe…

When samples have internal structure, we often see a mismatch between the objective optimized during training and the model's goal during inference. For example, in sequence-to-sequence modeling we are interested in high-quality translated sentences, but training typically uses maximum likelihood at the word level. The…

This paper focuses on learning rate analysis of distributed kernel ridge regression for strong mixing sequences. Using a recently developed integral operator approach and a classical covariance inequality for Banach-valued strong mixing sequences, we succeed in deriving optimal learning rate for distributed kernel ridg…

Adam optimization algorithm can have non-zero average regret under certain conditions.

Paper analyzes regret bounds for unconstrained online optimization.

ESPO optimizes LLMs for complex tasks by balancing fine-grained updates and stability.

Reinforcement Patching optimizes dynamic sequence patching for efficient time series forecasting.

Conditional COT-GAN predicts sequences using past data and kernel smoothing.

We obtain an index of the complexity of a random sequence by allowing the role of the measure in classical probability theory to be played by a function we call the generating mechanism. Typically, this generating mechanism will be a finite automata. We generate a set of biased sequences by applying a finite state auto…

This paper analyses the convergence and degeneration of sequences of metrics on a 3-manifold, and relations of such with Thurston's geometrization conjecture. The sequences are minimizing sequences for a certain (optimal) scalar-curvature type functional and their degeneration is related to the sphere and torus decompo…

The paper tackles online learning problems with monotone arm sequences, achieving optimal or near-optimal regret bounds.

Survey and benchmark high-dimensional Bayesian optimization of discrete sequences.

As deep learning techniques advance more than ever, hyper-parameter optimization is the new major workload in deep learning clusters. Although hyper-parameter optimization is crucial in training deep learning models for high model performance, effectively executing such a computation-heavy workload still remains a chal…

This paper studies stability of the exponential utility maximization when there are small variations on agent's utility function. Two settings are considered. First, in a general semimartingale model where random endowments are present, a sequence of utilities defined on R converges to the exponential utility. Under a …

A latent-variable model is introduced for text matching, inferring sentence representations by jointly optimizing generative and discriminative objectives. To alleviate typical optimization challenges in latent-variable models for text, we employ deconvolutional networks as the sequence decoder (generator), providing l…

An online framework optimizes efficiency in conformal prediction with a target miscoverage rate.