相关论文: Towards High Supervised Learning Utility Training …

Model-free reinforcement learning algorithms have seen remarkable progress, but key challenges remain. Trust Region Policy Optimization (TRPO) is known for ensuring monotonic policy improvement through conservative updates within a trust…

LLM pretraining is shifting from a compute-bound to a data-bound regime, where available human (organic) text falls far short of scaling demands. However, reaching the data-bound regime does not mean the model has fully utilized its organic…

We introduce dro, an open-source Python library for distributionally robust optimization (DRO) for regression and classification problems. The library implements 14 DRO formulations and 9 backbone models, enabling 79 distinct DRO methods.…

Despite recent advances in synthetic data generation, the scientific community still lacks a unified consensus on its usefulness. It is commonly believed that synthetic data can be used for both data exchange and boosting machine learning…

Recent progress in Large Language Model (LLM) reasoning is increasingly driven by the refinement of post-training loss functions and alignment strategies. However, standard Reinforcement Learning (RL) paradigms like Group Relative Policy…

Environments with procedurally generated content serve as important benchmarks for testing systematic generalization in deep reinforcement learning. In this setting, each level is an algorithmically created environment instance with a…

Alignment methodologies have emerged as a critical pathway for enhancing language model alignment capabilities. While SFT (supervised fine-tuning) accelerates convergence through direct token-level loss intervention, its efficacy is…

Tabular language models can generate synthetic tables by modeling rows as token sequences, but they are typically trained once with supervised fine-tuning and then used as static synthesizers. This is limiting because next-token likelihood…

Deep neural networks (DNN) are prone to miscalibrated predictions, often exhibiting a mismatch between the predicted output and the associated confidence scores. Contemporary model calibration techniques mitigate the problem of…

Tabular data synthesis is an emerging approach to circumvent strict regulations on data privacy while discovering knowledge through big data. Although state-of-the-art AI-based tabular data synthesizers, e.g., table-GAN, CTGAN, TVAE, and…

In the era of data-driven decision-making, accurate table-level representations and efficient table recommendation systems are becoming increasingly crucial for improving table management, discovery, and analysis. However, existing…

Deep convolutional neural networks are shown to be overkill with high parametric and computational redundancy in many application scenarios, and an increasing number of works have explored model pruning to obtain lightweight and efficient…

Reinforcement Learning with Verifiable Rewards (RLVR) has significantly advanced the reasoning capabilities of Large Language Models (LLMs). However, methods such as GRPO and DAPO suffer from substantial computational cost, since they rely…

Synthetic data serves as an alternative in training machine learning models, particularly when real-world data is limited or inaccessible. However, ensuring that synthetic data mirrors the complex nuances of real-world data is a challenging…

Training a deep neural network to maximize a target objective has become the standard recipe for successful machine learning over the last decade. These networks can be optimized with supervised learning, if the target objective is…

Traditionally, Knowledge Distillation (KD) is used for model compression, often leading to suboptimal performance. In this paper, we evaluate the impact of combining KD loss with alternative pruning techniques, including Low-Rank…

Machine Learning (ML) in low-data settings remains an underappreciated yet crucial problem. Hence, data augmentation methods to increase the sample size of datasets needed for ML are key to unlocking the transformative potential of ML in…

With the increasing availability of data for Prognostics and Health Management (PHM), Deep Learning (DL) techniques are now the subject of considerable attention for this application, often achieving more accurate Remaining Useful Life…

Existing post-training techniques are broadly categorized into supervised fine-tuning (SFT) and reinforcement learning (RL) methods; the former is stable during training but suffers from limited generalization, while the latter, despite its…

Privacy, data quality, and data sharing concerns pose a key limitation for tabular data applications. While generating synthetic data resembling the original distribution addresses some of these issues, most applications would benefit from…