English
Related papers

Related papers: Profile Likelihoods on ML-Steroids

200 papers

The scaling of Large Multimodal Models (LMMs) is constrained by the quality-quantity trade-off inherent in synthetic data. Previous approaches, such as LLM-as-a-Judge, have proven their effectiveness in addressing this but suffer from…

Artificial Intelligence · Computer Science 2026-05-11 Jinhao Jing , Qiannian Zhao , Chao Huang , Zhan Su

The increasing complexity of modern neural network architectures demands fast and memory-efficient implementations to mitigate computational bottlenecks. In this work, we evaluate the recently proposed BitNet architecture in HEP…

High Energy Physics - Phenomenology · Physics 2026-02-12 Claudius Krause , Daohan Wang , Ramon Winterhalder

While metrics available during pre-training, such as perplexity, correlate well with model performance at scaling-laws studies, their predictive capacities at a fixed model size remain unclear, hindering effective model selection and…

Computation and Language · Computer Science 2025-10-17 Hansi Zeng , Kai Hui , Honglei Zhuang , Zhen Qin , Zhenrui Yue , Hamed Zamani , Dana Alon

Hybrid parallelism underpins large-scale LLM training across tens of thousands of GPUs. At such scale, hardware failures on individual devices lead to performance skew across devices, diminishing overall training efficiency. Existing…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-05-12 Tenghui Ma , Jihu Guo , Wei Gao , Sitian Lu , Zhisheng Ye , Hanjing Wang , Dahua Lin

Recent studies have shown that Large Language Models (LLMs) struggle to accurately retrieve information and maintain reasoning capabilities when processing long-context inputs. To address these limitations, we propose a finetuning approach…

Machine Learning · Computer Science 2024-10-15 Zheyang Xiong , Vasilis Papageorgiou , Kangwook Lee , Dimitris Papailiopoulos

We consider the task of obtaining the maximum a posteriori estimate of discrete pairwise random fields with arbitrary unary potentials and semimetric pairwise potentials. For this problem, we propose an accurate hierarchical move making…

Artificial Intelligence · Computer Science 2012-05-14 M. Pawan Kumar , Daphne Koller

Theoretical guarantees are established for a standard estimator in a semi-parametric finite mixture model, where each component density is modeled as a product of univariate densities under a conditional independence assumption. The focus…

Statistics Theory · Mathematics 2025-11-07 Marie Du Roy de Chaumaray , Michael Levine , Matthieu Marbac

The rapid development of pretrained Machine Learning Interatomic Potentials (MLIPs) that cover a wide range of molecular species has made it challenging to select the best model for a given application. We benchmark 15 pretrained MLIPs,…

Chemical Physics · Physics 2026-04-22 Peter Eastman , Evan Pretti , Thomas E. Markland

Choice modellers routinely acknowledge the risk of convergence to inferior local optima when using structures other than a simple linear-in-parameters logit model. At the same time, there is no consensus on appropriate mechanisms for…

Econometrics · Economics 2025-06-04 Stephane Hess , David Bunch , Andrew Daly

While critical for alignment, Supervised Fine-Tuning (SFT) incurs the risk of catastrophic forgetting, yet the layer-wise emergence of instruction-following capabilities remains elusive. We investigate this mechanism via a comprehensive…

Machine Learning · Computer Science 2026-04-15 Qinghua Zhao , Xueling Gong , Xinyu Chen , Zhongfeng Kang , Xinlu Li

Hyperparameter (HP) optimization of deep learning (DL) is essential for high performance. As DL often requires several hours to days for its training, HP optimization (HPO) of DL is often prohibitively expensive. This boosted the emergence…

Machine Learning · Computer Science 2023-06-30 Shuhei Watanabe

Supervised fine-tuning (SFT) is a pivotal approach to adapting large language models (LLMs) for downstream tasks; however, performance often suffers from the ``seesaw phenomenon'', where indiscriminate parameter updates yield progress on…

Computation and Language · Computer Science 2025-09-22 Yao Wang , Di Liang , Minlong Peng

RooFit and RooStats, the toolkits for statistical modelling in ROOT, are used in most searches and measurements at the Large Hadron Collider as well as at $B$ factories. Larger datasets to be collected at e.g. the High-Luminosity LHC will…

Mathematical Software · Computer Science 2020-12-03 Stephan Hageboeck

Complex phenomena in engineering and the sciences are often modeled with computationally intensive feed-forward simulations for which a tractable analytic likelihood does not exist. In these cases, it is sometimes necessary to estimate an…

Methodology · Statistics 2020-06-18 Niccolò Dalmasso , Ann B. Lee , Rafael Izbicki , Taylor Pospisil , Ilmun Kim , Chieh-An Lin

Linear programming (LP) is an extremely useful tool and has been successfully applied to solve various problems in a wide range of areas, including operations research, engineering, economics, or even more abstract mathematical areas such…

Data Structures and Algorithms · Computer Science 2020-03-19 Agniva Chowdhury , Palma London , Haim Avron , Petros Drineas

Boolean satisfiability (SAT) is a fundamental NP-complete problem with many applications, including automated planning and scheduling. To solve large instances, SAT solvers have to rely on heuristics, e.g., choosing a branching variable in…

Artificial Intelligence · Computer Science 2023-07-19 Mikhail Shirokikh , Ilya Shenbin , Anton Alekseev , Sergey Nikolenko

Modern large language models become multimodal, analyzing various data formats like text and images. While fine-tuning is effective for adapting these multimodal language models (MLMs) to downstream tasks, full fine-tuning is…

Computation and Language · Computer Science 2025-12-01 Alexander Sergeev , Evgeny Kotelnikov

Recent advancements in Large Language Models (LLMs) have led to increasingly diverse requests, accompanied with varying resource (compute and memory) demands to serve them. However, this in turn degrades the cost-efficiency of LLM serving…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-06-06 Youhe Jiang , Fangcheng Fu , Xiaozhe Yao , Guoliang He , Xupeng Miao , Ana Klimovic , Bin Cui , Binhang Yuan , Eiko Yoneki

Profile-guided optimizations rely on profile data for directing compilers to generate optimized code. To achieve the maximum performance boost, profile data needs to be collected on the same version of the binary that is being optimized. In…

Programming Languages · Computer Science 2024-01-31 Amir Ayupov , Maksim Panchenko , Sergey Pupyrev

Hawkes Processes have undergone increasing popularity as default tools for modeling self- and mutually exciting interactions of discrete events in continuous-time event streams. A Maximum Likelihood Estimation (MLE) unconstrained…

Machine Learning · Computer Science 2021-05-11 Rafael Lima