Related papers: Fisher-Guided Selective Forgetting: Mitigating The…

Reinforcement Learning from Human Feedback (RLHF) has emerged as a powerful approach for aligning generative models, but its reliance on learned reward models makes it vulnerable to mis-specification and reward hacking. Preference-based…

Parameter-Efficient Fine-Tuning (PEFT) has emerged as a key strategy for adapting large-scale pre-trained models to downstream tasks, but existing approaches face notable limitations. Addition-based methods, such as Adapters, introduce…

Catastrophic forgetting has been a major challenge in continual learning, where the model needs to learn new tasks with limited or no access to data from previously seen tasks. To tackle this challenge, methods based on knowledge…

The key distinguishing property of a Bayesian approach is marginalization instead of optimization, not the prior, or Bayes rule. Bayesian inference is especially compelling for deep neural networks. (1) Neural networks are typically…

The problem of learning to generalize to unseen classes during training, known as few-shot classification, has attracted considerable attention. Initialization based methods, such as the gradient-based model agnostic meta-learning (MAML),…

Differentiable Filters, as recursive Bayesian estimators, possess the ability to learn complex dynamics by deriving state transition and measurement models exclusively from data. This data-driven approach eliminates the reliance on explicit…

In recent years deep neural networks have been successfully applied to the domains of reinforcement learning \cite{bengio2009learning,krizhevsky2012imagenet,hinton2006reducing}. Deep reinforcement learning \cite{mnih2015human} is reported…

The Fisher information matrix (FIM) is a fundamental quantity to represent the characteristics of a stochastic model, including deep neural networks (DNNs). The present study reveals novel statistics of FIM that are universal among a wide…

In this paper, we propose a method for privacy-preserving federated learning that uses randomly selected model parameters to update global models. High-quality deep neural networks (DNN) models require a huge amount of training data in…

Continual learning (CL) aims to train models on a sequence of tasks while retaining performance on previously learned ones. A core challenge in this setting is catastrophic forgetting, where new learning interferes with past knowledge.…

Recently mean field theory has been successfully used to analyze properties of wide, random neural networks. It gave rise to a prescriptive theory for initializing feed-forward neural networks with orthogonal weights, which ensures that…

In distributed optimization, the practical problem-solving performance is essentially sensitive to algorithm selection, parameter setting, problem type and data pattern. Thus, it is often laborious to acquire a highly efficient method for a…

As a promising paradigm to collaboratively train models with decentralized data, Federated Learning (FL) can be exploited to fine-tune Large Language Models (LLMs). While LLMs correspond to huge size, the scale of the training data…

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…

In a recent article we described a new type of deep neural network - a Perpetual Learning Machine (PLM) - which is capable of learning 'on the fly' like a brain by existing in a state of Perpetual Stochastic Gradient Descent (PSGD). Here,…

Position bias is a critical problem in information retrieval when dealing with implicit yet biased user feedback data. Unbiased ranking methods typically rely on causality models and debias the user feedback through inverse propensity…

Based on the predictive map theory of spatial learning in animals, this study delves into the dynamics of Successor Feature (SF) and Predecessor Feature (PF) algorithms within noisy environments. Utilizing Q-learning and Q($\lambda$)…

Federated learning (FL) offers privacy-preserving decentralized machine learning, optimizing models at edge clients without sharing private data. Simultaneously, foundation models (FMs) have gained traction in the artificial intelligence…

Federated Learning provides a privacy-preserving paradigm for distributed learning, but suffers from statistical heterogeneity across clients. Personalized Federated Learning (PFL) mitigates this issue by considering client-specific models.…

Learning a good representation is an essential component for deep reinforcement learning (RL). Representation learning is especially important in multitask and partially observable settings where building a representation of the unknown…