English
Related papers

Related papers: EMA Without the Lag: Bias-Corrected Iterate Averag…

200 papers

The Expectation-Maximization (EM) algorithm is a popular choice for learning latent variable models. Variants of the EM have been initially introduced, using incremental updates to scale to large datasets, and using Monte Carlo (MC)…

Machine Learning · Statistics 2022-03-22 Belhal Karimi , Ping Li

Many popular adaptive gradient methods such as Adam and RMSProp rely on an exponential moving average (EMA) to normalize their stepsizes. While the EMA makes these methods highly responsive to new gradient information, recent research has…

Machine Learning · Computer Science 2021-10-13 Brett Daley , Christopher Amato

Large Language Models (LLMs) trained for average correctness often exhibit mode collapse, producing narrow decision behaviors on tasks where multiple responses may be reasonable. This limitation is particularly problematic in ordinal…

Artificial Intelligence · Computer Science 2026-02-04 Eric Yang , Jong Ha Lee , Jonathan Amar , Elissa Ye , Yugang Jia

Recent work discovered Emergent Misalignment (EM): fine-tuning large language models on narrowly harmful datasets can lead them to become broadly misaligned. A survey of experts prior to publication revealed this was highly unexpected,…

Machine Learning · Computer Science 2025-06-16 Edward Turner , Anna Soligo , Mia Taylor , Senthooran Rajamanoharan , Neel Nanda

Neural networks are very effective when trained on large datasets for a large number of iterations. However, when they are trained on non-stationary streams of data and in an online fashion, their performance is reduced (1) by the online…

Machine Learning · Computer Science 2023-07-04 Albin Soutif--Cormerais , Antonio Carta , Joost Van de Weijer

Finetuning large language models on narrowly harmful datasets can cause them to become emergently misaligned, giving stereotypically `evil' responses across diverse unrelated settings. Concerningly, a pre-registered survey of experts failed…

Artificial Intelligence · Computer Science 2026-02-10 Anna Soligo , Edward Turner , Senthooran Rajamanoharan , Neel Nanda

Ideally, a meta-analysis will summarize data from several unbiased studies. Here we consider the less than ideal situation in which contributing studies may be compromised by measurement error. Measurement error affects every study design,…

Controlling robots through natural language is pivotal for enhancing human-robot collaboration and synthesizing complex robot behaviors. Recent works that are trained on large robot datasets show impressive generalization abilities.…

Diffusion models currently dominate the field of data-driven image synthesis with their unparalleled scaling to large datasets. In this paper, we identify and rectify several causes for uneven and ineffective training in the popular ADM…

Computer Vision and Pattern Recognition · Computer Science 2024-03-21 Tero Karras , Miika Aittala , Jaakko Lehtinen , Janne Hellsten , Timo Aila , Samuli Laine

What exactly do efficient sequence models gain over simple temporal averaging? We use exponential moving average (EMA) traces, the simplest recurrent context (no gating, no content-based retrieval), as a controlled probe to map the boundary…

Computation and Language · Computer Science 2026-04-13 Arth Singh

Machine learning (ML) is increasingly applied to optimize system performance in tasks such as resource management and network simulation. Unlike traditional ML tasks (e.g., image classification), networked systems often operate in…

Machine Learning · Computer Science 2026-05-15 Daiyang Yu , Xinyu Chen , Yihan Zhang , Yan Liang , Yaqi Qiao , Fan Lai

Large language models are becoming the go-to solution for the ever-growing number of tasks. However, with growing capacity, models are prone to rely on spurious correlations stemming from biases and stereotypes present in the training data.…

Computation and Language · Computer Science 2024-05-30 Tomasz Limisiewicz , David Mareček , Tomáš Musil

While recent test-time adaptations exhibit efficacy by adjusting batch normalization to narrow domain disparities, their effectiveness diminishes with realistic mini-batches due to inaccurate target estimation. As previous attempts merely…

Computer Vision and Pattern Recognition · Computer Science 2024-04-16 Zixian Su , Jingwei Guo , Kai Yao , Xi Yang , Qiufeng Wang , Kaizhu Huang

Lookahead-based acceleration methods, such as Nesterov's momentum, are widely used in optimization, but they often become unreliable in deep learning training mainly due to stochastic gradient noise and non-convex loss landscapes. In…

Machine Learning · Computer Science 2026-05-26 Chung-Yiu Yau , Dawei Li , Athanasios Glentis , Valentyn Boreiko , Hoi-To Wai , Mingyi Hong

Evolutionary algorithms (EAs) are general-purpose problem solvers that usually perform an unbiased search. This is reasonable and desirable in a black-box scenario. For combinatorial optimization problems, often more knowledge about the…

Neural and Evolutionary Computing · Computer Science 2020-04-23 Vahid Roostapour , Jakob Bossek , Frank Neumann

Several phenomena are available representing market activity: volumes, number of trades, durations between trades or quotes, volatility - however measured - all share the feature to be represented as positive valued time series. When…

Statistical Finance · Quantitative Finance 2021-07-14 Fabrizio Cipollini , Giampiero M. Gallo

Mixture-of-Experts (MoE) architectures enhance the efficiency of large language models by activating only a subset of experts per token. However, standard MoE employs a fixed Top-K routing strategy, leading to redundant computation and…

Artificial Intelligence · Computer Science 2026-05-15 Juntong Wu , Jialiang Cheng , Qishen Yin , Yue Dai , Yuliang Yan , Fuyu Lv , Ou Dan , Li Yuan

Continual Instruction Tuning (CIT) is adopted to continually instruct Large Models to follow human intent data by data. It is observed that existing gradient update would heavily destroy the performance on previous datasets during CIT…

Machine Learning · Computer Science 2025-12-15 Jingyang Qiao , Zhizhong Zhang , Xin Tan , Yanyun Qu , Shouhong Ding , Yuan Xie

Evaluating true metacognition in Large Language Models (LLMs) is difficult due to biases and heuristics. This paper presents a framework to measure and enhance LLM metacognition while controlling for these biases. A measurement method using…

Neural and Evolutionary Computing · Computer Science 2026-05-26 Sangjun Park , Elliot Meyerson , Xin Qiu , Risto Miikkulainen

Effectiveness of speech emotion recognition in real-world scenarios is often hindered by noisy environments and variability across datasets. This paper introduces a two-step approach to enhance the robustness and generalization of speech…

Sound · Computer Science 2025-10-13 Upasana Tiwari , Rupayan Chakraborty , Sunil Kumar Kopparapu