English
Related papers

Related papers: Reconsidering the Past: Optimizing Hidden States i…

200 papers

Language model (LM) agents deployed in novel environments often exhibit poor sample efficiency when learning from sequential interactions. This significantly hinders the usefulness of such agents in environments where interaction is costly…

Machine Learning · Computer Science 2026-01-06 Michael Y. Hu , Benjamin Van Durme , Jacob Andreas , Harsh Jhamtani

Recent advances in linguistic steganalysis have successively applied CNN, RNN, GNN and other efficient deep models for detecting secret information in generative texts. These methods tend to seek stronger feature extractors to achieve…

Computation and Language · Computer Science 2022-02-03 Biao Yi , Hanzhou Wu , Guorui Feng , Xinpeng Zhang

The state transition algorithm (STA), as an intelligent optimization method grounded in constructivist learning, has been demonstrated to be highly effective in solving complex optimization problems. However, the standard STA suffers from…

Optimization and Control · Mathematics 2026-04-30 Xiaojun Zhou , Chunhua Yang , Weihua Gui , Tingwen Huang

We enhance auto-regressive language models by conditioning on document chunks retrieved from a large corpus, based on local similarity with preceding tokens. With a $2$ trillion token database, our Retrieval-Enhanced Transformer (RETRO)…

Given a query and dataset, the optimal way of answering the query is to make use all the information available. Modern LLMs exhibit impressive ability to memorize training data, but data not deemed important during training is forgotten,…

Computation and Language · Computer Science 2025-06-17 Evan Becker , Benjamin Bowman , Matthew Trager , Tian Yu Liu , Luca Zancato , Wei Xia , Stefano Soatto

We explore the idea of automatically crafting a tuning dataset for Statistical Machine Translation (SMT) that makes the hyper-parameters of the SMT system more robust with respect to some specific deficiencies of the parameter tuning…

Computation and Language · Computer Science 2017-10-03 Preslav Nakov , Stephan Vogel

In high-dimensional statistics, variable selection recovers the latent sparse patterns from all possible covariate combinations. This paper proposes a novel optimization method to solve the exact L0-regularized regression problem, which is…

Methodology · Statistics 2022-06-02 Mingzhang Yin , Nhat Ho , Bowei Yan , Xiaoning Qian , Mingyuan Zhou

There is a clear need for efficient algorithms to tune hyperparameters for statistical learning schemes, since the commonly applied search methods (such as grid search with N-fold cross-validation) are inefficient and/or approximate.…

Machine Learning · Computer Science 2020-04-07 Luis Miguel Lopez-Ramos , Baltasar Beferull-Lozano

Configuration optimization remains a critical bottleneck in machine learning, requiring coordinated tuning across model architecture, training strategy, feature engineering, and hyperparameters. Traditional approaches treat these dimensions…

Artificial Intelligence · Computer Science 2025-08-22 Yuxing Lu , Yucheng Hu , Nan Sun , Xukai Zhao

Setting regularization parameters for Lasso-type estimators is notoriously difficult, though crucial in practice. The most popular hyperparameter optimization approach is grid-search using held-out validation data. Grid-search however…

Continual learning aims to learn multiple tasks sequentially while preserving prior knowledge, but faces the challenge of catastrophic forgetting when adapting to new tasks. Recently, approaches leveraging pre-trained models have gained…

Computer Vision and Pattern Recognition · Computer Science 2025-11-12 Quan Cheng , Yuanyu Wan , Lingyu Wu , Chenping Hou , Lijun Zhang

This paper studies how a stochastic gradient algorithm (SG) can be controlled to hide the estimate of the local stationary point from an eavesdropper. Such problems are of significant interest in distributed optimization settings like…

Machine Learning · Computer Science 2024-05-14 Adit Jain , Vikram Krishnamurthy

Language modeling on large-scale datasets leads to impressive performance gains on various downstream language tasks. The validation pre-training loss (or perplexity in autoregressive language modeling) is often used as the evaluation…

Machine Learning · Computer Science 2022-10-26 Hong Liu , Sang Michael Xie , Zhiyuan Li , Tengyu Ma

The hidden Markov model (HMM) is a fundamental tool for sequence modeling that cleanly separates the hidden state from the emission structure. However, this separation makes it difficult to fit HMMs to large datasets in modern NLP, and they…

Computation and Language · Computer Science 2020-11-10 Justin T. Chiu , Alexander M. Rush

Offline reinforcement learning (RL) aims to find a near-optimal policy using pre-collected datasets. In real-world scenarios, data collection could be costly and risky; therefore, offline RL becomes particularly challenging when the…

Machine Learning · Computer Science 2024-12-18 Ruizhe Shi , Yuyao Liu , Yanjie Ze , Simon S. Du , Huazhe Xu

Simultaneous translation (ST) starts translations synchronously while reading source sentences, and is used in many online scenarios. The previous wait-k policy is concise and achieved good results in ST. However, wait-k policy faces two…

Computation and Language · Computer Science 2020-12-24 Shaolei Zhang , Yang Feng , Liangyou Li

Latent structure models are a powerful tool for modeling language data: they can mitigate the error propagation and annotation bottleneck in pipeline systems, while simultaneously uncovering linguistic insights about the data. One challenge…

Computation and Language · Computer Science 2020-10-07 Tsvetomila Mihaylova , Vlad Niculae , André F. T. Martins

The rapid growth of large language models (LLMs) with traditional centralized fine-tuning emerges as a key technique for adapting these models to domain-specific challenges, yielding privacy risks for both model and data owners. One…

Computation and Language · Computer Science 2025-07-08 Kai Yao , Zhaorui Tan , Penglei Gao , Lichun Li , Kaixin Wu , Yinggui Wang , Yuan Zhao , Yixin Ji , Wei Wang , Jianke Zhu

Pretrained language models have achieved state-of-the-art performance when adapted to a downstream NLP task. However, theoretical analysis of these models is scarce and challenging since the pretraining and downstream tasks can be very…

Machine Learning · Computer Science 2022-04-22 Colin Wei , Sang Michael Xie , Tengyu Ma

Few-Shot Aspect-Based Sentiment Analysis (FSABSA) is an indispensable and highly challenging task in natural language processing. However, methods based on Pre-trained Language Models (PLMs) struggle to accommodate multiple sub-tasks, and…

Computation and Language · Computer Science 2024-08-20 Baoxing Jiang , Yujie Wan , Shenggen Ju