New findings suggest non-contrastive learning has many bad minima, not just collapsed ones.
problem The effectiveness of non-contrastive learning in unsupervised feature learning.
method Theoretical analysis and controlled experiments on simple data models.
result Non-contrastive losses have a preponderance of non-collapsed bad minima, and these minima are not avoided during training.
Simplified non-contrastive learning avoids representation collapse.
problem Training failure modes in self-supervised learning.
method Hyperdimensional computing and inductive bias.
result The approach avoids representation collapses.
New method proves non-contrastive self-supervised learning learns useful features.
problem Understanding how non-contrastive self-supervised learning (NS-SL) learns useful features.
method Proved in a linear network, NS-SL learns a desirable projection matrix and reduces sample complexity. Suggested weight decay acts as an implicit threshold.
result DirectCopy, a simpler and more efficient algorithm, outperforms DirectPred on various datasets.
Develops a new self-supervised learning method combining contrastive and non-contrastive approaches.
problem Leveraging unlabeled data for representation learning, especially with high variance and low batch sizes.
method Converts a contrastive method (Spectral Contrastive Loss) into a non-contrastive form (MINC loss) to reduce variance and mutual information.
result MINC loss consistently improves upon the Spectral Contrastive loss baseline in learning image representations.
SupSiam and SupBYOL improve supervised representation learning with ANCL.
problem Improving supervised representation learning with ANCL.
method Proposed supervised ANCL framework leveraging labels to avoid collapse.
result Supervised ANCL improves representation learning across various datasets and tasks.
New method removes contrastive loss by adding a prediction head, revealing learning mechanisms.
problem Understanding why neural networks learn competitive representations despite trivial optima.
method Empirical and theoretical analysis of a trainable, identity-initialized prediction head.
result The trainable prediction head enables learning all features, preventing dimensional collapse.
Feature normalization prevents collapse in non-contrastive learning dynamics.
problem Non-contrastive learning can collapse into a single point due to lack of repulsive force.
method Extended previous theory based on L2 loss to cosine loss, considering feature normalization.
result Cosine loss induces stable equilibrium, preventing collapse even with insufficient repulsive force.
VJE learns latent representations without contrastive learning, providing probabilistic semantics.
problem Learning latent representations without contrastive signals.
method VJE maximizes a symmetric conditional evidence lower bound (ELBO) on paired encoder embeddings, using a Student-t distribution on a polar representation.
result VJE outperforms standard non-contrastive baselines in ImageNet-1K, CIFAR-10/100, and STL-10.
This work defines idealized SSL representations and improves existing methods.
problem Unclear characteristics of SSL representations leading to high downstream accuracies.
method Characterized ideal properties and derived necessary and sufficient conditions.
result Improved SSL methods and derived new objectives for contrastive and non-contrastive learning.
Unified framework for SSL methods linking contrastive and non-contrastive approaches.
problem Lack of theoretical foundations and design guidelines for SSL methods.
method Spectral manifold learning framework to unify SSL methods.
result Theoretical bridge between contrastive and non-contrastive methods.
Kernel-based SSL creates useful representations without labels.
problem Creating useful representations without labels using self-supervised learning.
method Derive methods for kernel-based SSL, focusing on contrastive and non-contrastive loss functions.
result Kernel-induced representations correlate related points and de-correlate unrelated ones.
Unified framework for self-supervised learning via latent distribution matching.
problem Lack of a unifying theoretical framework for diverse SSL methods.
method Casting SSL as latent distribution matching (LDM): maximizing alignment and uniformity.
result Derives a Bayesian filtering model and proves identifiable latent representations.
Proposes a framework to extract ordered eigenfunctions from contextual kernels.
problem Lack of exact spectral decomposition in existing methods.
method Modular building blocks for compatibility with contextual kernels and scalability.
result Extracted eigenfunctions provide effective importance scores for feature selection.
Deep learning for TOF-MRA without matched training data.
problem High-quality reconstruction from undersampled TOF-MRA.
method Two-stage unsupervised deep learning approach using cycleGAN theory.
result Exceeds performance of state-of-the-art CS-based methods.
CurvSSL improves SSL by aligning local manifold curvature.
problem Improving self-supervised learning by capturing local manifold geometry.
method CurvSSL augments Barlow Twins with a curvature-based regularizer to align and decorrelate embeddings across augmentations.
result Curvature-regularized SSL yields competitive or improved linear evaluation performance.
Gaussian graphical models (GGMs) are probabilistic tools of choice for analyzing conditional dependencies between variables in complex systems. Finding changepoints in the structural evolution of a GGM is therefore essential to detecting anomalies in the underlying system modeled by the GGM. In order to detect structur…
Model identifies causal structure from paired observational and interventional data with unknown soft interventions.
problem Identifying causal structure from observational and interventional data with unknown soft interventions.
method Proposes a scalable causal discovery model that aggregates subset-level PDAGs and applies contrastive cross-regime orientation rules.
result The model asymptotically recovers the identifiable PDAG and can orient additional edges compared to non-contrastive subset-restricted methods.
Meta-learning adapts models for unseen tasks across AI, robotics, and NLP.
problem Adapting models to unseen tasks efficiently and accurately.
method Black-box, metric-based, layered, and Bayesian approaches.
result Meta-learning enhances model generalization and adaptation to unseen tasks.
Meta-learning improves neural networks by adapting learning algorithms.
problem Conventional AI approaches solve tasks from scratch, but meta-learning aims to improve the learning algorithm.
method Meta-learning adapts a learning algorithm based on multiple learning episodes.
result Meta-learning can tackle deep learning challenges like data and computation bottlenecks.
Survey explores how transfer learning improves deep reinforcement learning.
problem Challenges in reinforcement learning efficiency and effectiveness.
method Categorizes and analyzes transfer learning approaches.
result Transfer learning enhances reinforcement learning performance.
Machine learning models adapt to motor learning but face challenges.
problem Adapting machine learning to handle motor variability and differentiate new movements from known ones.
method Parameter adaptation, transfer and meta-learning, reinforcement learning.
result Challenges in applying machine learning models for motor learning support systems.
New method uses bi-level optimization to learn useful representations for imitation learning.
problem Learning useful representations for multiple tasks in imitation learning settings.
method Formulates representation learning as a bi-level optimization problem.
result Bi-level optimization framework provides sample complexity benefits for imitation learning.
Tabular Q-Learning with learned state abstractions solves continuous control tasks.
problem Challenging reinforcement learning problems in continuous control.
method Learned state abstraction to transform continuous state-space into discrete.
result Tabular Q-Learning with learned abstractions achieves efficient learning in unseen tasks.
Study Whittle index learning algorithms for restless bandits with constant stepsizes.
problem Optimizing decisions in restless multi-armed bandits with constant stepsizes.
method Developed Q-learning algorithms with constant stepsizes for index learning in restless bandits, extending to DQN and function approximations.
result The algorithms learn the Whittle index effectively.
Paper discusses flaws in traditional RL for lifelong learning.
problem Traditional RL fails to model lifelong learning systems.
method Simplified prototype of lifelong RL system.
result Insights into lifelong RL, showing traditional RL's limitations.
AI learns to learn sequentially without forgetting.
problem Preventing catastrophic forgetting in machine learning models.
method Meta-learning a neuromodulatory activation-gating function to control selective activation in deep neural networks.
result State-of-the-art continual learning performance with 600 classes (9,000 updates).
Poisson learning doesn't solve graph semi-supervised learning issues.
problem Global information loss in graph-based semi-supervised learning.
method Poisson learning is Laplace regularization with thresholding.
result Poisson learning cannot overcome the global information loss problem.
New unsupervised learning technique learns independent kernels for better machine learning tasks.
problem Improving unsupervised representation learning for machine learning tasks.
method Stacking convolutional transforms using alternating proximal minimization scheme.
result DCTL outperforms shallow version CTL on benchmark datasets.
Meta-learning helps models learn quickly from few samples.
problem Deep learning requires many samples, which are hard to get.
method Meta-learning optimizes models to adapt quickly to new tasks.
result Meta-learning can improve model efficiency and adaptability.
New self-imitation learning method improves performance in continuous control tasks.
problem Improving off-policy learning in continuous control tasks.
method Proposes a n-step lower bound to generalize lower-bound Q-learning and introduces a new family of self-imitation learning algorithms.
result n-step lower bound Q-learning achieves a better trade-off between bias and contraction rate, leading to improved performance.
Deep reinforcement learning finds optimal learning policies for adaptive systems.
problem Finding individualized learning plans for learners with unknown latent traits.
method Formulated as a Markov decision process, applied deep Q-learning with a transition model estimator.
result The algorithm efficiently discovers optimal learning policies with small data sets.
Unified framework explains all types of learning, including brain.
problem Lack of clear explanation for deep learning success.
method Constructing a learning principle that equates all learning to probability estimation.
result Unified understanding of learning across different fields.
Cyclical learning rates improve DRL performance without manual tuning.
problem Manual hyperparameter tuning in DRL is time-consuming and error-prone.
method Proposes cyclical learning rates for DRL problems.
result Cyclical learning achieves similar or better results than fixed learning rates.
Study batch reinforcement learning methods for personalized medical treatments.
problem Batch reinforcement learning for personalized medical treatments.
method Direct policy learning and model-based learning approaches.
result Model-based learning is impossible with finite model classes but feasible with relaxed conditions.
A new meta-meta classification method tackles few-shot learning tasks.
problem Learning with limited data in small-data settings.
method Designing an ensemble of learners for a large set of problems, then learning how to combine them for a new problem.
result Meta-meta classification outperforms traditional meta-learning and ensembling approaches in one-shot learning tasks.
The paper proposes a learning algorithm that improves adaptability and generalization.
problem Improving adaptability and generalization in learning models.
method Learning to meta-learn by meta-finetuning on related tasks before adapting to specific tasks.
result Learning to meta-learn improves adaptability and generalization across various tasks.
This paper surveys meta-learning, online, and continual learning.
problem Combining and understanding meta-learning, online, and continual learning.
method Organizing various problem settings using consistent terminology and formal descriptions.
result Fosters further advancements in meta-learning, online, and continual learning.
Relational logistic regression (RLR) is a representation of conditional probability in terms of weighted formulae for modelling multi-relational data. In this paper, we develop a learning algorithm for RLR models. Learning an RLR model from data consists of two steps: 1- learning the set of formulae to be used in the m…
Survey on curriculum learning for reinforcement learning.
problem Efficiently learning complex tasks in reinforcement learning.
method Framework for curriculum learning in reinforcement learning.
result Survey and classification of existing CL methods.
Contrastive learning works well with redundant data views.
problem Improving unsupervised learning with redundant data views.
method Theoretical analysis of contrastive learning in a multi-view setting.
result Linear functions of learned representations are nearly optimal on prediction tasks when views are redundant.
Paper analyzes iterative learning for concept classes and learns half-spaces.
problem Learning concept classes efficiently with iterative learners.
method Analyzes various settings of iterative learning and provides a constructive algorithm for half-spaces.
result Constructive iterative algorithm for learning half-spaces from informant.
This paper introduces Dex, a reinforcement learning environment toolkit specialized for training and evaluation of continual learning methods as well as general reinforcement learning problems. We also present the novel continual learning method of incremental learning, where a challenging environment is solved using o…
Study shows cliff-learning in transfer learning from foundation models.
problem Data-scaling of transfer learning from foundation models in low data regimes.
method Investigation of cliff-learning phenomenon through foundation-model analysis and toy models.
result Cliff-learning reflects compatibility between priors and tasks.
Meta-strategy learns tuning parameters for online learning methods.
problem Difficulty in setting tuning parameters for online learning methods.
method Meta-learning approach to learn parameters from past tasks.
result Meta-strategy improves on learning each task in isolation.
We discuss a general method to learn data representations from multiple tasks. We provide a justification for this method in both settings of multitask learning and learning-to-learn. The method is illustrated in detail in the special case of linear feature learning. Conditions on the theoretical advantage offered by m…
Compared to reinforcement learning, imitation learning (IL) is a powerful paradigm for training agents to learn control policies efficiently from expert demonstrations. However, in most cases, obtaining demonstration data is costly and laborious, which poses a significant challenge in some scenarios. A promising altern…
Machine can learn its own bias from related tasks.
problem Machine learning bias through hand-crafted features.
method Introduces two models: PAC-based and hierarchical Bayes.
result Machine can learn bias from multiple tasks.
This paper aims to define out-of-distribution learning.
problem Lack of formal definitions for out-of-distribution learning.
method Chronological approach using PAC learning framework.
result Established a universally agreed-upon approach to quantify different types of learning.