EBMs improve continual learning without external memory or regularization.
problem Improving continual learning without external memory or regularization.
method Energy-Based Models with contrastive divergence training objective.
result EBMs outperform baseline methods on various benchmarks.
Continuous time framework for discrete data denoising models.
problem Efficient training and sampling for discrete data denoising models.
method Formulated as Continuous Time Markov Chains (CTMCs), efficient training using continuous time ELBO, high-dimensional CTMC simulation, novel theoretical error bound.
result Continuous time treatment enables novel theoretical error bound between generated and true data distributions.
3D good continuation model explains stereo vision using neurogeometry.
problem Understanding how the brain processes 3D visual correspondence.
method Developed a neurogeometric model involving spatial and orientation disparities.
result Provides insight into neural organization and correspondence problem.
In this paper, we show how to construct graph theoretical models of n-dimensional continuous objects and manifolds. These models retain topological properties of their continuous counterparts. An LCL collection of n-cells in Euclidean space is introduced and investigated. If an LCL collection of n-cells is a cover of a…
Paper proves method for calculating NML code length works for continuous models.
problem Uncertainty in calculating NML code length for continuous models.
method Introduced a novel decomposition approach based on the coarea formula to prove correctness for continuous cases.
result Method accurately calculates NML code length for continuous models.
Study builds a Japanese financial-specific LLM through continual pre-training.
problem Lack of domain-specific Japanese financial LLMs.
method Continual pre-training on Japanese financial-focused datasets using a base Japanese LLM.
result Tuned model outperforms original model on Japanese financial benchmarks.
New insights into continual learning for deep models, showing convergence issues but local linear solutions.
problem Challenges in continual learning for homogeneous deep models.
method Sequential projections onto task margin sets, leveraging nonconvex projection theory.
result Local linear convergence under certain conditions for homogeneous deep networks.
New algorithm for aggregate inference in HMMs with continuous observations.
problem Inference in large populations with indistinguishable individuals and continuous measurements.
method Continuous observation collective forward-backward algorithm extending existing discrete case algorithm.
result Efficacy demonstrated through numerical experiments.
Study analyzes a new algorithm for complex optimization problems.
problem Stochastic bilevel optimisation problems in continuous-time models.
method Continuous-time, two-timescale stochastic approximation algorithm.
result Obtained weak convergence rate using central limit theorem.
The study tackles modeling high-frequency financial data using continuous distributions, finding them inadequate.
problem Challenges in modeling high-frequency integer price changes with continuous distributions.
method Proposed a modified maximum likelihood estimation procedure to account for the discreteness of high-frequency price changes.
result Traditional GARCH models are not suitable for high-frequency data due to the discreteness of price changes.
Formulates superhedging under costs and uncertainty for continuous assets.
problem Superhedging with transaction costs and model uncertainty for continuous processes.
method New topological framework for continuous asset prices with parametric model uncertainty.
result Formulates a superhedging theorem in the presence of transaction costs and model uncertainty.
Hybrid model combines continuous and tractable probabilistic models.
problem Intractable probabilistic inference in continuous latent-space models.
method Continuous mixtures of tractable probabilistic models with finite integration points.
result Hybrid models achieve state-of-the-art performance in density estimation.
Neural SDEs model continuous sequences using neural networks.
problem Modeling continuous-time dynamics in sequence data.
method Interprets time-series as samples from a continuous dynamical system, parameterized by Neural SDE.
result Demonstrates superior performance in diverse sequence modeling tasks.
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.
Continuous semi-implicit models enable faster training and better performance in generative modeling.
problem Slow convergence in hierarchical semi-implicit models during training.
method CoSIM, a continuous semi-implicit model that incorporates a continuous transition kernel for efficient training.
result CoSIM achieves superior performance on image generation tasks compared to existing methods.
Continuous-time model shows insider trading constraints impact market dynamics.
problem Trading constraints faced by insiders in continuous-time models.
method Proved global existence of equilibrium with terminal trading constraint.
result Equilibrium model aligns with empirical market behaviors.
Efficient method for learning continuous exponential families beyond Gaussian.
problem Learning continuous exponential families with unbounded support.
method Interaction Screening approach for scalable learning of continuous graphical models.
result Our estimator maintains similar accuracy and sample complexity scalings compared to alternative approaches, while improving run-time.
New RL framework models continuous-time dynamics using neural ODEs.
problem Modeling continuous-time dynamics in semi-Markov decision processes.
method Model-based reinforcement learning with neural ODEs.
result High-performing policies developed with minimal data.
Continuous-time MBRL framework tackles control systems with Bayesian ODEs.
problem Discretization of continuous-time systems in MBRL.
method Novel actor-critic method with Bayesian ODEs for state inference.
result Model robust against irregular and noisy data, sample-efficient, solves challenging control problems.
This paper develops variational continual learning (VCL), a simple but general framework for continual learning that fuses online variational inference (VI) and recent advances in Monte Carlo VI for neural networks. The framework can successfully train both deep discriminative models and deep generative models in compl…
Consider power utility maximization of terminal wealth in a 1-dimensional continuous-time exponential Levy model with finite time horizon. We discretize the model by restricting portfolio adjustments to an equidistant discrete time grid. Under minimal assumptions we prove convergence of the optimal discrete-time strate…
We study the stability of several no-arbitrage conditions with respect to absolutely continuous, but not necessarily equivalent, changes of measure. We first consider models based on continuous semimartingales and show that no-arbitrage conditions weaker than NA and NFLVR are always stable. Then, in the context of gene…
Proposes a continuous, differentiable model from local adaptive models.
problem Inadequate continuity and differentiability in over-parameterized models.
method A global continuous and differentiable model constructed from weighted averages of locally learned models.
result Achieves faster statistical convergence and improved performance in various settings.
Bayesian approach helps update deep models without forgetting past data.
problem Updating deep models sequentially without forgetting past data.
method Bayesian inference for continual learning.
result Bayesian approach enables updating model beliefs with new data.
Estimating causal models from observational data is a crucial task in data analysis. For continuous-valued data, Shimizu et al. have proposed a linear acyclic non-Gaussian model to understand the data generating process, and have shown that their model is identifiable when the number of data is sufficiently large. Howe…
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.
We discuss replica analytic continuation using several simple models in order to prove mathematically the validity of replica analysis, which is used in a wide range of fields related to large scale complex systems. While replica analysis consists of two analytical techniques, the replica trick (or replica analytic con…
Unified continuous diffusion model outperforms discrete alternatives in scalability and quality.
problem Continuous diffusion models were perceived as less scalable than discrete models.
method Reconstructed Plaid model and compared it with modern discrete DLMs, optimizing noise schedule and embeddings via likelihood.
result Unified continuous diffusion model (RePlaid) outperforms discrete models in compute efficiency and quality.
Proposes Mv-TCNN for continual learning without known tasks in advance.
problem Catastrophic forgetting in continual learning.
method Multi-view Task Conditional Neural Networks (Mv-TCNN).
result Outperforms state-of-the-art continual learning models.
CANDI solves the gap between continuous and discrete diffusion models for text generation.
problem Underperformance of continuous diffusion models in discrete data domains.
method Introduces token identifiability and a hybrid framework (CANDI) to decouple discrete and continuous corruption.
result CANDI successfully avoids temporal dissonance, enabling continuous diffusion benefits for discrete spaces.
Flow based models such as Real NVP are an extremely powerful approach to density estimation. However, existing flow based models are restricted to transforming continuous densities over a continuous input space into similarly continuous distributions over continuous latent variables. This makes them poorly suited for m…
DFMs enable flow-based models for multimodal discrete and continuous data.
problem Combining discrete and continuous data for generative models.
method Discrete Flow Models (DFMs) using Continuous Time Markov Chains.
result DFMs achieve state-of-the-art co-design performance for protein structure and sequence generation.
A new clustering model for mixed datasets combines continuous and non-continuous data.
problem Challenges in clustering mixed data due to heterogeneous variables.
method Mixed Deep Gaussian Mixture Model (MDGMM) with multilayer architecture.
result Automatic selection of model specifications and optimal number of clusters.
EVCL combines VCL and EWC to prevent forgetting new tasks.
problem Preventing catastrophic forgetting in continual learning.
method Hybrid model integrating VCL and EWC.
result Consistently outperforms baselines in learning new tasks.
Generalizes PCA and ICA for continuous-time signals using neural networks.
problem Low-rank decomposition of continuous-time vector-valued signals.
method Implicit neural network framework to learn numerical approximations of PCA and ICA.
result Unified approach to PCA and ICA in continuous domain, enforcing decorrelation and independence.
Study on continual learning with Twitter data, developing ConGraD algorithm.
problem Personalized online language learning on a massive scale.
method Developed POLL problem setting, collected Firehose datasets, and introduced ConGraD algorithm.
result ConGraD algorithm outperforms prior continual learning methods on Firehose datasets.
VAIOM models financial returns using continuous input and categorical output.
problem Modeling continuous, noisy, and heterogeneous financial data.
method VAIOM is a decoder-only Transformer that separates input representation from output likelihood.
result VAIOM models outperform fixed single-bar LightGBM baseline in both Test halves.
This paper tackles continuous domain generalization, improving model performance across unseen domains.
problem Existing domain generalization approaches fail to capture the complex, multidimensional nature of real-world variation.
method Introduces Continuous Domain Generalization (CDG), a principled framework grounded in geometric and algebraic theories. Proposes a Neural Lie Transport Operator (NeuralLio) for structure-preserving parameter transitions and a gating mechanism for robust generalization.
result Demonstrates significant improvement in generalization accuracy and robustness across various datasets.
ADER addresses continual learning in session-based recommendation by periodically replaying exemplars with adaptive distillation.
problem Catastrophic forgetting in continual learning of session-based recommenders.
method Periodically replaying previous training samples (exemplars) with an adaptive distillation loss.
result ADER consistently outperforms other continual learning techniques and even all historical data at every update cycle.
DLM-One speeds up language generation by 500x with continuous models.
problem Efficiently generating text sequences in natural language processing.
method Score-distillation of continuous diffusion language models.
result Achieves up to 500x speedup in inference time with competitive performance.
CIPNN model tackles continuous latent variables, solving intractable posterior problems.
problem Solving intractable posterior calculation for continuous latent variables.
method Derives analytical solution for posterior of continuous latent variables, proposes CIPNN and CIPAE.
result CIPNN model demonstrates great classification capability, solving problems for continuous latent variables.
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.
Paper tackles continual reinforcement learning by forgetting, proposing a planning method with online world models.
problem Catastrophic forgetting in reinforcement learning when learning new tasks.
method Planning with an online world model using model predictive control.
result The proposed FTL Online Agent (OA) learns new tasks without forgetting old skills.
Topic models are probabilistic models for discovering topical themes in collections of documents. In real world applications, these models provide us with the means of organizing what would otherwise be unstructured collections. They can help us cluster a huge collection into different topics or find a subset of the co…
Paper proposes copula-based models for analyzing multivariate zero-inflated continuous data.
problem Challenges in analyzing multivariate zero-inflated continuous data with mixed discreteness and continuity.
method Proposes two copula-based density estimation models and rectified Gaussian copula.
result Demonstrates superior performance compared to conventional methods.
Acute kidney injury (AKI) commonly occurs in hospitalized patients and can lead to serious medical complications. In order to optimally predict AKI before it develops at any time during a hospital stay, we present a novel framework in which AKI is continually predicted automatically from EHR data over the entire hospit…
Study robust utility maximization with uncertain continuous semimartingales.
problem Maximizing utility in continuous time under model uncertainty.
method Duality and conjugate problems for logarithmic, exponential, and power utilities.
result Existence of optimal portfolios for various utilities.
Bilevel Continual Learning improves continual learning by transferring knowledge effectively.
problem Catastrophic forgetting and poor generalization in continual learning.
method Bilevel optimization and dual memory management strategies.
result BCL achieves effective knowledge transfer and alleviates catastrophic forgetting.