Paper defines continuous rotation representations for neural networks.
problem Discontinuous representations of rotations in neural networks.
method Definition of continuous representations, relating to topological concepts.
result Continuous representations for 3D rotations in 5D and 6D are more suitable for neural networks.
OML learns representations to prevent forgetting in continual learning.
problem Continual learning agents forget existing knowledge when learning new data.
method OML directly minimizes catastrophic interference by learning representations that facilitate future learning.
result OML learns representations that accelerate future learning and are robust to forgetting.
Paper proposes SDRL to improve continual learning with less computational cost.
problem Catastrophic forgetting in continual learning.
method SDRL method that refines gradients from memorized samples to reduce gradient diversity.
result SDRL shows better performance than state-of-the-art methods on multiple benchmark tasks.
The paper shows how continuous attention can lead to better object representations.
problem Learning good representations from data without labeled examples.
method Integrating unsupervised learning and reinforcement learning with intrinsic motivation.
result The proposed algorithm improves object recognition in few-shot settings.
Paper proposes continual learning for sentence encoders.
problem Optimize sentence encoders for new corpora while maintaining old corpus accuracy.
method Initialize encoders with corpus-independent features, update using Boolean operations of conceptor matrices.
result Proposed sentence encoder can continually learn features from new corpora.
Paper proposes a new FRL algorithm for continuous sensitive attributes using EIPM.
problem Existing FRL algorithms cannot handle continuous sensitive attributes.
method Introduces EIPM to assess fairness in representation space for continuous attributes and proposes FREM algorithm.
result FREM outperforms other methods in fairness evaluation for continuous sensitive attributes.
Representations based on random walks can exploit discrete data distributions for clustering and classification. We extend such representations from discrete to continuous distributions. Transition probabilities are now calculated using a diffusion equation with a diffusion coefficient that inversely depends on the dat…
S-TRIGGER learns state representations for continual learning.
problem Efficiently compress and maintain past knowledge in changing environments.
method Generative Replay with self-triggered environment change detection.
result S-TRIGGER enables fast and high-performing Reinforcement Learning without catastrophic forgetting.
Paper defines conditions for limit sets of Anosov representations to be smooth submanifolds.
problem Understanding the smoothness of limit sets of Anosov representations.
method Established conditions for limit sets to be differentiable submanifolds and calculated optimal Holder constants.
result Limit sets of projective Anosov representations are differentiable submanifolds with Holder continuous derivatives.
Paper tackles overestimation bias in continuous control, improving performance by 25%.
problem Overestimation bias in off-policy learning.
method Truncated Quantile Critics (TQC) combines distributional representation, truncation, and ensembling of critics.
result TQC outperforms state-of-the-art methods by 25% on the Humanoid environment.
We present a framework for learning disentangled and interpretable jointly continuous and discrete representations in an unsupervised manner. By augmenting the continuous latent distribution of variational autoencoders with a relaxed discrete distribution and controlling the amount of information encoded in each latent…
Temporal-difference (TD) networks are a class of predictive state representations that use well-established TD methods to learn models of partially observable dynamical systems. Previous research with TD networks has dealt only with dynamical systems with finite sets of observations and actions. We present an algorithm…
Proposes continuous graph neural networks to capture long-range dependencies.
problem Capturing long-range dependencies in graph data.
method Defines continuous dynamics for graph neural networks using diffusion-based methods.
result Proposed continuous graph neural networks are effective and deeper networks can capture long-range dependencies.
Earth observation embeddings can convert discrete biome maps into continuous representations that better capture ecological variation.
problem Biome maps impose categorical boundaries that compress continuous variation in biotic communities.
method Fit a linear classifier on Earth observation embeddings to predict biome labels.
result Continuous biome representation outperforms discrete biome labels for predicting species occurrence.
Maximal representations in symplectic lattices proven for most cases.
problem Understanding maximal representations in symplectic lattices.
method Analyzing mapping class group orbits and continuous deformations of maximal diagonal representations.
result Proof of maximal representations in most lattices of Sp(2n,R).
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.
Dual representations for robust risk measures and uncertainty sets.
problem Characterizing continuity of robust risk measures and their uncertainty sets.
method Develop dual representations for robust risk measures and uncertainty sets based on distinct geometric assumptions.
result Two dual frameworks for consolidated uncertainty sets are complementary, not interchangeable.
We classify hyperbolic monopoles with continuous symmetries and construct new examples.
problem Classifying and constructing hyperbolic monopoles with continuous symmetries.
method Developed a Structure Theorem and used representation theory to simplify the problem.
result Found constraints on structure groups and constructed novel spherically symmetric Sp(n) hyperbolic monopoles. Framework for continuous-time network data representation learning.
problem Learning reliable representations of dynamic network interactions.
method Three-stage process: intensity estimation, projection learning, evolving node representation construction.
result Trajectories satisfy structural and temporal coherence, providing robust inference.
Study shows how deep network representations can be transferred between datasets and tasks.
problem Transferability of deep network representations across datasets and tasks.
method Examined layer-wise transferability of representations in deep networks across multiple datasets and tasks.
result Interesting empirical observations on layer-wise transferability of representations.
Framework learns portable representations for diverse tasks.
problem Creating task-independent abstract representations for diverse environments.
method Autonomously learns portable representations in egocentric space.
result Portable representations enable task-independent planning and transfer.
Develops correlation number for specific potentials and Hitchin representations.
problem Analyzing correlation numbers for potentials with entropy gaps and Hitchin representations.
method Defines a correlation number for pairs of cusped Hitchin representations and explores its connection to the Manhattan curve.
result Establishes a connection between the correlation number and the Manhattan curve, revealing rigidity properties.
DeepCCG adapts classifiers to representation shifts in one step.
problem Adapting classifiers to shifts in continuous representation.
method Empirical Bayesian approach using class conditional Gaussian classifier and KL divergence for selection.
result DeepCCG reduces performance change due to representation shifts.
American options can be equivalent to European options under certain conditions.
problem Determining when American options can be simplified to European options.
method Using methods from Jourdain and Martini, Chrsitensen, and convex duality.
result A first step towards verifying representability of American options.
Many loss functions in representation learning are invariant under a continuous symmetry transformation. For example, the loss function of word embeddings (Mikolov et al., 2013) remains unchanged if we simultaneously rotate all word and context embedding vectors. We show that representation learning models for time ser…
A new framework for graph representation learning.
problem Acquiring continuous representations of discrete objects like graphs.
method Nested SubSpace (NSS) arrangement and Disk-ANChor ARrangement (DANCAR).
result Successfully embedded WordNet in 20-dimensional space with high F1 score.
A new image representation method using hypernetworks.
problem Representing images in a way that allows for continuous manipulation and analysis.
method Constructing a hypernetwork that maps pixel positions to colors, allowing for continuous image manipulation.
result Comparable image super-resolution results to existing methods using a single model.
A new method uncovers discrete and continuous factors in gene expression data.
problem Jointly identifying discrete and continuous factors of variability without supervision.
method cpl-mixVAE framework using multiple interacting networks.
result The method successfully uncovers discrete and continuous factors in gene expression data.
New algorithm for context bandits with continuous actions.
problem Efficient decision-making with unknown action structures.
method Reduction-style algorithm combining supervised learning.
result Proven to work in general and validated with experiments.
Logit-Coordinate models improve representation of mixed data types.
problem Representation of mixed continuous-categorical data in generative models.
method Logit-coordinate framework combining categorical and continuous variables.
result Logit-Coordinate models outperform one-hot encoding in simulations and real data.
Method estimates causal effects from incremental data, overcoming missing data challenges.
problem Estimating causal effects from non-stationary, incrementally available observational data.
method Continual Causal Effect Representation Learning
result Method achieves continual causal effect estimation without compromising original data.
Theory of Θ-positive representations for real closed fields.
problem Generalizing positive representations to real closed fields.
method Developing theory for Fuchsian groups to linear groups over real closed fields.
result Theory encompasses many generalizations of positive or Anosov representations.
Replicated and validated Rank-N-Contrast for robust regression.
problem Deep regression models struggle with continuous sample orders.
method Contrastive learning of continuous representations by ranking samples.
result Improved performance and robustness of RNC framework.
DINo forecasts PDEs with flexible extrapolation and adaptability.
problem Fixed discretizations limit real-world PDE forecasting.
method DINo uses implicit neural representations for continuous-time dynamics.
result DINo outperforms other neural PDE forecasters.
Hybrid framework prevents forgetting in continual learning.
problem Avoiding forgetting in learning new tasks without forgetting old ones.
method Hybrid continual learning framework combining architecture growth and experience replay.
result Hybrid approach effectively avoids forgetting across multiple tasks.
A graph VAE framework optimizes neural architectures in a continuous space.
problem Discovering efficient neural architectures in a discrete space.
method Graph VAE framework with VAE and GNN components, joint learning of predictors and decoders.
result The framework discovers powerful neural architectures with both excellent performance and high computational efficiency.
Adaptive tensor modeling preserves continuity in multidimensional data.
problem Discretization of continuous multidimensional data loses important information.
method Functional Tucker decomposition (FTD) with RKHS modeling.
result FTD enables adaptive and expressive tensor modeling.
Characterizes continuity of monotone functionals in mixed topology.
problem Continuity of monotone functionals in mixed topology.
method Characterization through lower semicontinuity and dual representations.
result Continuity in mixed topology is equivalent to dual representation in terms of countably additive measures.
CLPF models continuous time-series data with improved representational power and variational approximations.
problem Fitting continuous time-series data with existing models faces challenges in representational power and variational quality.
method CLPF uses a time-dependent normalizing flow driven by a stochastic differential equation to decode continuous latent processes into continuous observables. Maximum likelihood optimization is achieved through a novel variational posterior process.
result CLPF outperforms state-of-the-art baselines on synthetic and real-world time-series data.
We consider the problem of building a state representation model in a continual fashion. As the environment changes, the aim is to efficiently compress the sensory state's information without losing past knowledge. The learned features are then fed to a Reinforcement Learning algorithm to learn a policy. We propose to …
New model-independent compact representations of imaginary-time data are presented in terms of the intermediate representation (IR) of analytical continuation. This is motivated by a recent numerical finding by the authors [J. Otsuki et al., arXiv:1702.03056]. We demonstrate the efficiency of the IR through continuous-…
Introduces CHL, a new loss function for continuous similarity learning.
problem Binary similarity learning limitations.
method CHL is a novel loss function that generalizes histogram loss to continuous similarities.
result CHL solves a wider range of tasks including similarity learning, representation learning, and data visualization.
Neural networks can represent complex piecewise functions efficiently.
problem Representing continuous piecewise affine functions with neural networks.
method Two hidden layers with ReLU activation, O(p) neurons for p pieces. result CPA functions can be represented by a neural network with linear size.
We continue our discussion from part I.
CURL tackles unsupervised continual learning without task labels.
problem Learning from non-stationary distributions without task labels.
method Dynamic representation learning without task labels, incorporating rehearsal techniques.
result Strong performance in unsupervised and supervised settings.
New representation of PSL2(R) on infinite hyperbolic space via convex bodies.
problem Continuous irreducible actions of PSL2(R) on infinite-dimensional hyperbolic space.
method Using hyperbolic model for convex bodies, produce a continuous and irreducible representation.
result Yields a convex cocompact PSL2(R)-action on infinite-dimensional hyperbolic space with specific quotient properties.
Stochastic representation for determinants derived from Brownian loop soups.
problem Determinants of Laplace-type operators on manifolds.
method Stochastic representation using Brownian loop soups.
result Derives continuity of determinants and conformal invariance on surfaces.
Foundation models fail to preserve continuous geometry, identified as the Geometric Alignment Tax.
problem Continuous geometry is lost in foundation models due to discrete categorical bottlenecks.
method Controlled ablations on synthetic systems and evaluation of 14 biological models using rate-distortion theory and MINE.
result Replacing cross-entropy with a continuous head reduces geometric distortion by up to 8.5x.