Related papers: Teacher Forcing as Generalized Bayes: Optimization…

Federated learning algorithms perform reasonably well on independent and identically distributed (IID) data. They, on the other hand, suffer greatly from heterogeneous environments, i.e., Non-IID data. Despite the fact that many research…

This work presents a formalism to improve the predictive accuracy of physical models by learning generalizable augmentations from sparse data. Building on recent advances in data-driven turbulence modeling, the present approach, referred to…

Auxiliary information can be exploited in machine learning models using the paradigm of evidence based conditional inference. Multi-modal techniques in Deep Neural Networks (DNNs) can be seen as perturbing the latent feature representation…

Information-theoretic (IT) generalization bounds have been used to study the generalization of learning algorithms. These bounds are intrinsically data- and algorithm-dependent so that one can exploit the properties of data and algorithm to…

Non-stationarity can arise in Reinforcement Learning (RL) even in stationary environments. For example, most RL algorithms collect new data throughout training, using a non-stationary behaviour policy. Due to the transience of this…

Standard fine-tuning of language models typically performs well on in-distribution data, but suffers with generalization to distribution shifts. In this work, we aim to improve the generalization of adapter-based cross-lingual task transfer…

Interactive Information Retrieval (IIR) and Reinforcement Learning (RL) share many commonalities, including an agent who learns while interacts, a long-term and complex goal, and an algorithm that explores and adapts. To successfully apply…

In this paper, we study the problem of balancing effectiveness and efficiency in automated feature selection. Feature selection is a fundamental intelligence for machine learning and predictive analysis. After exploring many feature…

With the concept of teaching being introduced to the machine learning community, a teacher model start using dynamic loss functions to teach the training of a student model. The dynamic intends to set adaptive loss functions to different…

The performance of Large Language Models (LLMs) on natural language tasks can be improved through both supervised fine-tuning (SFT) and in-context learning (ICL), which operate via distinct mechanisms. Supervised fine-tuning updates the…

The generalization of model-based reinforcement learning (MBRL) methods to environments with unseen transition dynamics is an important yet challenging problem. Existing methods try to extract environment-specified information $Z$ from past…

Longitudinal NLP tasks require reasoning over temporally ordered text to detect persistence and change in human behavior and opinions. However, in-context learning with large language models struggles on tasks where models must integrate…

Centralized training is the standard paradigm in deep learning, enabling models to learn from a unified dataset in a single location. In such setup, isotropic feature distributions naturally arise as a mean to support well-structured and…

In order to tackle the difficulty associated with the ill-posed nature of the image registration problem, regularization is often used to constrain the solution space. For most learning-based registration approaches, the regularization…

Test-time training (TTT) methods explicitly update the weights of a model to adapt to the specific test instance, and they have found success in a variety of settings, including most recently language modeling and reasoning. To demystify…

Federated Learning is a fast growing area of ML where the training datasets are extremely distributed, all while dynamically changing over time. Models need to be trained on clients' devices without any guarantees for either homogeneity or…

Instruction Fine-Tuning enhances pre-trained language models from basic next-word prediction to complex instruction-following. However, existing One-off Instruction Fine-Tuning (One-off IFT) method, applied on a diverse instruction, may not…

Weak-to-strong generalization, where a student model trained on imperfect labels generated by a weaker teacher nonetheless surpasses that teacher, has been widely observed but the mechanisms that enable it have remained poorly understood.…

The Teacher-Student Framework (TSF) is a reinforcement learning setting where a teacher agent guards the training of a student agent by intervening and providing online demonstrations. Assuming optimal, the teacher policy has the perfect…

The label distribution skew induced data heterogeniety has been shown to be a significant obstacle that limits the model performance in federated learning, which is particularly developed for collaborative model training over decentralized…