Paper demystifies AD techniques for efficient deep learning.
problem Generalizing backpropagation for complex neural networks.
method Uncovering reverse-mode AD and its connection to delimited continuations, implementing it via operator overloading.
result Efficient reverse-mode AD without auxiliary data structures, combining deep learning and pure library approaches.
DELIMIT PyTorch enhances deep learning for diffusion imaging.
problem Applying deep learning to spherical diffusion imaging data.
method Added spherical harmonic interpolation and local convolution layers to PyTorch.
result Deep learning can now be applied conveniently to diffusion imaging data.
Paper proposes neural approach for Chinese named entity recognition.
problem Challenges in Chinese named entity recognition due to context-dependency and lack of word delimiters.
method Introduces a CNN-LSTM-CRF neural architecture and a unified framework for joint training with word segmentation.
result Improves Chinese named entity recognition performance, especially with limited training data.
New formula connects Loewner energy to moving frames' renormalised energy.
problem Calculating Loewner energy of Jordan curves.
method Using renormalised energy of moving frames.
result Loewner energy as Kähler potential for Weil-Petersson space.
We initiate the mathematical study of spherical collapse of self-gravitating charged scalar fields. The main result gives a complete characterization of the future boundary of spacetime, providing a starting point for studying the cosmic censorship conjectures. In general, the boundary includes two null components, one…
New method optimizes tail dependence coefficient estimation.
problem Estimating tail dependence in nonparametric data.
method Optimal threshold selection combining mean squared error and copula estimation.
result Improved accuracy in tail dependence coefficient estimation.
The paper introduces GAER to assess market feasibility under geopolitical and institutional constraints.
problem Feasibility of adaptive market efficiency under heterogeneous institutional and geopolitical conditions.
method Structural framework integrating adaptive market theory, institutional economics, and political economy.
result GAER as a diagnostic indicator for portfolio construction feasibility.
The superfamily phenomenon of time series with different dynamics can be characterized by the motif rank patterns observed in the nearest-neighbor networks of the time series in phase space. However, the determinants of superfamily classification are unclear. We attack this problem by studying the influence of linear t…
Optimal income crossover found using particle swarm optimization.
problem Determining the crossover point between two income distributions.
method Particle swarm optimization for finding crossover income, temperature, and Pareto index.
result Optimization method finds boundaries of two income distributions.
In this work, an ensemble of economic interacting agents is considered. The agents are arranged in a linear array where only local couplings are allowed. The deterministic dynamics of each agent is given by a map. This map is expressed by two factors. The first one is a linear term that models the expansion of the agen…
Paper tackles counterfactual sentence detection and evaluation.
problem Detect and evaluate counterfactual sentences in natural language.
method Used a BERT base model for classification and a hybrid BERT Multi-Layer Perceptron for sequence identification. Introduced cascaded linear inputs to improve performance.
result Achieved an F1 score of 85.00% in Task 1 and 83.90% in Task 2.
IMeL turns RL into SL by interpolating improved experiences.
problem Improving reinforcement learning efficiency and scalability.
method IMeL uses a reservoir of experiences and a NN regressor for interpolation.
result IMeL achieves preliminary results and proposes itself as a baseline.
Method estimates curvature of submanifolds using hypersurface integral invariants.
problem Estimating curvature of submanifolds in high dimensions.
method Integral invariants from PCA on hypersurface domains.
result Eigenvalues and eigenvectors as multi-scale curvature estimators.
Study finds long-term linear correlations in Chinese stock order aggressiveness.
problem Investigating long-term correlations in order aggressiveness of Chinese stocks.
method Used detrending moving average and multifractal detrending moving average analyses on order flow data.
result Strong long-term linear correlations found in order aggressiveness, with some exceptions.
A phase transition affects loss landscape and generalization in neural networks.
problem Understanding the transition between under- and over-parametrization in neural networks.
method Analytical and empirical study of fully-connected networks with hinge loss.
result The generalization error shows three phases: initial decay, increase until a cusp, and slow decay.
TCDA separates observation space and causal assumptions for stable summaries.
problem Undefined or inadequate outcomes in modern data.
method Separates observation space, causal-model class, and topological representation.
result Identification and stability of causal effects through topology.
New method recovers signals from noisy indirect data, even when noise is uncertain.
problem Recovering signals from indirect observations with uncertain noise.
method Polyhedral estimates, incorporating convex optimization.
result Presumably good estimates can be constructed for ellitope signal sets.
Study finds no significant short-term impact on liquidity supply after protocol fees were reduced.
problem Liquidity provider welfare is affected by protocol fees, but the impact on liquidity supply is unclear.
method Used a matched-overlap event-study difference-in-differences design to estimate the liquidity-supply response to take-rate cuts.
result No significant short-term impact on active liquidity or local depth; no change in LP participation or composition.
DSPM models control noise volatility, improving financial data analysis.
problem Financial returns exhibit volatility clustering, challenging traditional models.
method DSPM uses a tempered-stable subordinator to control noise volatility, preserving kurtosis and autocorrelation.
result DSPM models accurately capture volatility clustering and noise mechanisms.
The paper studies continuous submodular functions and their optimization.
problem Maximizing continuous submodular functions in poly. time.
method Characterization of continuous submodularity, operations preserving it, and algorithms for constrained maximization.
result Continuous submodularity is equivalent to a weak DR property, leading to continuous DR-submodular functions with the full DR property.
Solves complex Monge-Ampère equation with Hölder continuous boundary data.
problem Complex Monge-Ampère equation with Hölder continuous boundary data.
method Solves the Dirichlet problem for the complex Monge-Ampère equation.
result The solution is Hölder continuous if the boundary data is Hölder continuous.
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.
Defines continuous versions of combinatorial objects from lattice paths.
problem Lattice path enumeration and combinatorial identities.
method Continuous analog of lattice paths and binomials.
result Defines continuous versions of combinatorial objects.
Uniform Lipschitz continuity of isoperimetric profiles in evolving surfaces.
problem Uniform Lipschitz continuity of isoperimetric profiles in evolving surfaces.
method Normalized Ricci flow on compact surfaces.
result Uniform Lipschitz continuity of isoperimetric profiles under normalized Ricci flow.
The study proves unique continuation for biharmonic maps.
problem Unique continuation of biharmonic maps between manifolds.
method Proof of unique continuation results.
result Proves several unique continuation results for biharmonic maps.
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.
Continuized Nesterov acceleration accelerates stochastic gradient descent and gossip algorithms.
problem Improving the convergence rate of stochastic gradient descent and gossip algorithms.
method Introducing a continuized variant of Nesterov acceleration, which mixes variables continuously and takes gradient steps at random times.
result The continuized Nesterov acceleration achieves convergence rates similar to Nesterov's original acceleration but with random parameters.
Faster policy learning via continuous-time gradients.
problem Efficiently estimating policy gradients for continuous-time systems.
method Approximating continuous-time gradients directly, using adaptive discretization.
result More efficient policy gradient estimator leads to faster learning.
Current evaluations of continual learning are flawed and misleading.
problem Flawed experiment designs in current evaluations.
method Examine and propose new experiment designs.
result New experiment designs reveal true performance of continual learning approaches.
Classifies when homeomorphism groups of stable surfaces have automatic continuity.
problem Determining when homeomorphism groups of stable surfaces are continuous.
method Developed a general framework to prove automatic continuity for homeomorphism groups, applied to stable surfaces and Stone spaces.
result Classification of stable surfaces with respect to automatic continuity of their homeomorphism groups.
Framework learns disentangled continuous and categorical representations.
problem Learning disentangled representations of continuous and categorical data.
method Variational autoencoder with relaxed discrete distribution, controlling latent units.
result Framework disentangles continuous and categorical factors on various datasets.
Study on Hölder continuity of complex Monge-Ampère solutions on Stein spaces.
problem Understanding continuity of solutions to complex Monge-Ampère equations on Stein spaces.
method Analyzing solutions with Lp densities and Hölder boundary data on Stein spaces with isolated singularities. result Solutions are Hölder continuous outside singular points if boundary data is Hölder continuous.
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.
Characterizes Lipschitz continuity using microlocal sheaf theory.
problem Understanding Lipschitz continuity on differential manifolds.
method Microlocal sheaf theory applied to the graph of continuous maps.
result Characterization of Lipschitz continuity in microlocal terms.
Root's barrier is continuous and finite under certain conditions.
problem Continuity of the root barrier function.
method Analyzing Skorokhod embedding problem and properties of target measures.
result The barrier function is continuous and finite under specified conditions.
Study on existence and properties of continuous solutions to complex Hessian equations.
problem Existence and properties of continuous solutions to complex Hessian equations.
method Established new capacity estimates and weak stability estimates for the m-Hessian measure. result Existence of continuous solutions to the complex Hessian equation under certain conditions.
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.
The paper proves differentiability of evolution maps in Lie groups.
problem Differentiability of evolution maps in infinite-dimensional Lie groups.
method Showed sequential continuity (Mackey k-continuity) leading to differentiability.
result Differentiability of evolution maps in Ck-semiregular Lie groups. 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.
Continuity of Kähler-Einstein potentials at singularities proven.
problem Regularity of solutions to degenerate complex Monge-Ampère equations on singular spaces.
method Investigation of Dirichlet problem and global continuity of solutions.
result Kähler-Einstein potentials are continuous at isolated singularities.
Continuity of delta invariant leads to uniform Kähler-Einstein metrics.
problem Continuity of delta invariant in Kähler and twisted Kähler-Einstein metrics.
method Analytic delta invariant and uniform Yau-Tian-Donaldson theorem.
result Uniform Yau-Tian-Donaldson theorem for twisted Kähler-Einstein metrics.
Stochastic gradient descent in continuous time improves efficiency for complex models.
problem Efficiently learning and optimizing continuous-time models.
method Continuous-time stochastic gradient descent (SGDCT) using a stochastic differential equation.
result Convergence to optimal parameters over time, validated by theoretical analysis.
Proposes a framework for semi-supervised continual learning from sequentially arriving data.
problem Learning from data with changing task distribution over time, especially in domains with a mix of labeled and unlabeled data.
method Meta-Consolidation for Continual Semi-Supervised Learning (MCSSL) framework with a hypernetwork and semi-supervised auxiliary classifier.
result Significant improvements in continual semi-supervised learning setting.
Develops DPG methods for continuous-time RL with deterministic policies.
problem High variance and slow convergence in stochastic policy RL methods.
method Derives continuous-time policy gradient formula and proposes CT-DDPG algorithm.
result CT-DDPG achieves superior stability and faster convergence in continuous-time RL.
Improves continual learning with Variational Continual Learning framework.
problem Avoiding catastrophic forgetting and efficient model capacity use in sequential tasks.
method Mean-field variational Bayesian neural networks approach.
result Significantly improved results on continual learning benchmarks.
Study restrictions on digitally continuous functions and their effects.
problem Understanding effects of restrictions on digitally continuous functions.
method Analyzing digitally continuous functions and their modifications.
result Analogous result for topological spaces derived from digitally continuous functions.
In this paper we introduce a link between geometry of ordinary continued fractions and trajectories of points that moves according to the second Kepler law. We expand geometric interpretation of ordinary continued fractions to the case of continued fractions with arbitrary elements.
Develops analysis of Hölder continuous mappings on Heisenberg groups.
problem Analyzing Hölder continuous mappings on Heisenberg groups.
method Theory of distributional Jacobians and pullbacks of differential forms.
result Simple proof of a generalization of the Gromov non-embedding theorem and new results about Hölder homotopy groups.