Core-Halo solves large-scale fixed-point problems by decentralizing updates.
problem Large-scale fixed-point equations with block dependencies.
method Core-Halo decomposition separates write ownership from read-only context, aligning with block-dependence structure.
result Core-Halo achieves near-centralized performance while retaining parallelism.
The paper analyzes when credal sets stabilize under iterative updates in machine learning.
problem When do credal sets stabilize under iterative updates in machine learning?
method Fixed-point theorems for credal set updates.
result The paper provides the first analysis of credal set stability.
New method handles unknown task boundaries in continual learning.
problem Catastrophic forgetting in neural networks.
method Fixed-point equations for online variational Bayes optimization.
result Approximates online Bayes update for non-stationary data.
Finding a fixed point to a nonexpansive operator, i.e., x∗=Tx∗, abstracts many problems in numerical linear algebra, optimization, and other areas of scientific computing. To solve fixed-point problems, we propose ARock, an algorithmic framework in which multiple agents (machines, processors, or cores) update x i…
This work introduces a fixed-point optimization for variational inference.
problem Improving quantified uncertainty in predictions by optimizing a simplified distribution over parameters.
method Projective integral updates for high-dimensional variational inference.
result Efficient quasirandom quadrature sequence for mean-field distributions, leading to quasi-Newton variational Bayes (QNVB).
Mathematical methods characterize RNNs' asymptotics as hidden units and data grow.
problem Characterize recurrent neural networks' behavior as hidden units and data grow.
method Developed mathematical methods to analyze RNNs' convergence to an infinite-dimensional ODE coupled with a fixed point of a random algebraic equation.
result RNNs converge to an infinite-dimensional ODE coupled with a fixed point of a random algebraic equation.
New TD algorithms stabilize RL tasks by reformulating updates into fixed point equations.
problem TD learning's sensitivity to step size specification.
method Implicit TD algorithms reformulate TD updates into fixed point equations.
result Implicit TD algorithms are more stable and less sensitive to step size.
Develops accelerated fixed-point methods with delayed oracles for scientific computing.
problem Approximating fixed points of nonexpansive operators.
method Combines Nesterov's acceleration and KM iteration with delayed inexact oracles.
result Establishes improved convergence rates for fixed-point approximation.
A modern Hopfield network improves deep learning with better memory and attention.
problem Improving memory and attention mechanisms in deep learning.
method Introducing a new Hopfield network with continuous states and a novel update rule.
result The new Hopfield network can store and retrieve patterns efficiently with low errors.
The sum-product or belief propagation (BP) algorithm is a widely used message-passing technique for computing approximate marginals in graphical models. We introduce a new technique, called stochastic orthogonal series message-passing (SOSMP), for computing the BP fixed point in models with continuous random variables.…
New method stabilizes DEQ models by regularizing Jacobian of fixed-point equations.
problem Stability and performance of DEQ models.
method Jacobian regularization to stabilize DEQ models.
result Significant stabilization of fixed-point convergence in DEQ models.
Kolmogorov-Arnold Networks enable ultrafast online learning with fixed-point quantization.
problem Efficient online learning for high-frequency systems with strict memory constraints.
method Fixed-point online training on FPGAs exploiting B-spline locality in KANs.
result Kolmogorov-Arnold Networks are more efficient and expressive than MLPs for low-latency tasks.
Gradient-based clustering method for various cost functions.
problem Distance-based clustering for various cost functions.
method Iterative alternating update procedure for cluster assignments and centers.
result Converges to fixed points under mild assumptions.
GD converges in unstable regimes, even with oscillatory behavior.
problem Understanding convergence of GD in unstable regimes.
method Analysis of two-step gradient updates.
result Characterization of local conditions for convergence.
Motivated by a recent result of Daskalakis et al. 2018, we analyze the population version of Expectation-Maximization (EM) algorithm for the case of \textit{truncated} mixtures of two Gaussians. Truncated samples from a d-dimensional mixture of two Gaussians $\frac{1}{2} \mathcal{N}(\vecμ, \vecΣ)+ \frac{1}{2} \mathca…
FedSplit improves federated learning by ensuring correct convergence to optimal solutions.
problem Federated learning's fixed points do not always correspond to optimal solutions in simple convex settings.
method FedSplit uses operator splitting procedures to solve distributed convex minimization problems with additive structure.
result FedSplit ensures that the fixed points correspond to optima of the original optimization problem.
New method learns causal models from data efficiently.
problem Learning Structural Causal Models from data is challenging.
method Amortized inference via Conditional Fixed-Point Iterations with transformer embeddings.
result Single model predicts causal mechanisms conditioned on data and graph.
Quantile Temporal-Difference learning proved convergent with proof.
problem Lack of theoretical understanding of QTD despite empirical success.
method Proof of convergence using stochastic approximation and non-smooth analysis.
result QTD converges to fixed points with probability 1.
New TD method stabilizes average-reward learning.
problem Stability issues in average-reward TD learning.
method Implicit fixed point update for average-reward TD(λ). result Improved numerical stability and broader step-size range.
GRPO optimizes LLMs with verifiable rewards, amplifying policy success.
problem Improving LLMs' reasoning under verifiable binary rewards.
method Introduces GRPO, analyzes variants of reward normalization and regularization.
result GRPO amplifies policy success, converging to a fixed point exceeding the reference.
Traditional Kalman filter (KF) is derived under the well-known minimum mean square error (MMSE) criterion, which is optimal under Gaussian assumption. However, when the signals are non-Gaussian, especially when the system is disturbed by some heavy-tailed impulsive noises, the performance of KF will deteriorate serious…
The study analyzes sharpness dynamics in neural networks, revealing mechanisms and conditions.
problem Understanding sharpness in neural network training.
method Fixed point analysis and edge of stability analysis in a simplified 2-layer linear network.
result Reveals mechanisms behind sharpness trends, conditions for edge of stability, and a period-doubling route to chaos.
Gradient descent forces neural network eigenvalues to a specific threshold.
problem Understanding why gradient descent drives eigenvalues to a specific threshold.
method Introduced edge coupling, a functional on consecutive iterate pairs, to explain the trajectory towards the eigenvalue threshold.
result Gradient descent forces the Hessian eigenvalue to the threshold 2/η from arbitrary initialization. The policy gradient theorem describes the gradient of the expected discounted return with respect to an agent's policy parameters. However, most policy gradient methods drop the discount factor from the state distribution and therefore do not optimize the discounted objective. What do they optimize instead? This has be…
Over 50 years of work on group actions on 4-manifolds, from the 1960's to the present, from knotted fixed point sets to Seiberg-Witten invariants, is surveyed. Locally linear actions are emphasized, but differentiable and purely topological actions are also discussed. The presentation is organized around some of the …
REMAL: Residual Equilibrium Manifold Active Learning for Surrogate-Based Multidisciplinary Design Analysis
problem Multidisciplinary design analysis of coupled engineering systems requires solving equilibrium states where all disciplinary coupling variables are consistent.
method Residual manifold surrogate modeling framework for coupled systems.
result REMAL learns a surrogate model of the joint residual manifold via multitask Gaussian process models.
We propose a novel method to accelerate Lloyd's algorithm for K-Means clustering. Unlike previous acceleration approaches that reduce computational cost per iterations or improve initialization, our approach is focused on reducing the number of iterations required for convergence. This is achieved by treating the assig…
We present a method for performing Hamiltonian Monte Carlo that largely eliminates sample rejection for typical hyperparameters. In situations that would normally lead to rejection, instead a longer trajectory is computed until a new state is reached that can be accepted. This is achieved using Markov chain transitions…
The paper classifies circle actions on 6D manifolds with isolated fixed points.
problem Classifying circle actions on 6D manifolds with isolated fixed points.
method Performing equivariant connected sums at fixed points with specific manifolds.
result A sequence of operations can reduce the fixed point data to the empty collection.
An algorithm for computing positive semidefinite factorizations of matrices.
problem Computing positive semidefinite factorizations of matrices.
method Non-commutative extension of Lee-Seung's algorithm (Matrix Multiplicative Update, MMU).
result The MMU algorithm ensures PSD updates and achieves critical points.
Groups with special properties always have fixed points.
problem Groups acting on finite CW-complexes without fixed points.
method Exhibited specific groups with strong fixed-point properties.
result Groups with finite generation and torsion-freeness have global fixed points.
Recurrent neural networks (RNNs) are powerful dynamical models for data with complex temporal structure. However, training RNNs has traditionally proved challenging due to exploding or vanishing of gradients. RNN models such as LSTMs and GRUs (and their variants) significantly mitigate these issues associated with trai…
Develops a reinforcement learning algorithm for learning deterministic equilibrium policies in time-inconsistent control problems.
problem Learning equilibrium policies in time-inconsistent control problems.
method Continuous-time model-free reinforcement learning algorithm using deterministic policy gradient approach.
result Learned equilibrium policies in general time-inconsistent control problems.
Expectation propagation (EP) is a powerful approximate inference algorithm. However, a critical barrier in applying EP is that the moment matching in message updates can be intractable. Handcrafting approximations is usually tricky, and lacks generalizability. Importance sampling is very expensive. While Laplace propag…
Quantized neural networks can represent all fixed-point functions under certain conditions.
problem Expressive power of quantized neural networks under fixed-point arithmetic.
method Analyzing necessary and sufficient conditions for quantized networks to represent all fixed-point functions.
result Various popular activation functions satisfy the sufficient condition for representing all fixed-point functions.
Study circle actions on unitary manifolds with discrete fixed points.
problem Understanding circle actions on compact unitary manifolds with discrete fixed points.
method Prove relationships between weights at fixed points and derive results regarding the first equivariant Chern class and Hirzebruch χy-genus. result Derive a multigraph encoding fixed point data, leading to new insights into unitary S1-manifolds. Research shows quadratic growth in derivative maxima for certain interval diffeos with parabolic fixed points.
problem Analyzing the growth of derivative maxima for C2 interval diffeomorphisms with parabolic fixed points. method Examining C2 diffeomorphisms with only parabolic fixed points, focusing on tangency and repelling behavior. result Maximal growth of derivative maxima is exactly quadratic for diffeomorphisms with a non-quadratic tangency to identity at a repelling fixed point.
New proof for 6D symplectic manifold with 4 fixed points.
problem Classifying the integral cohomology ring and total Chern class for 6D symplectic manifolds with 4 fixed points.
method New different argument using moment map values and weights of fixed points.
result Determined the sets of weights and global invariants for the manifold.
The paper highlights issues with fixed point claims in digital images.
problem Flaws in published assertions about fixed points in digital images.
method Continues a series of studies examining digital topology.
result Identifies and discusses problems with fixed point claims.
The paper highlights issues in fixed point claims in digital topology.
problem Flaws in published assertions about fixed points in digital metric spaces.
method Continues a series of studies examining these flaws.
result Identifies and discusses problems in fixed point claims.
Neural network has attracted great attention for a long time and many researchers are devoted to improve the effectiveness of neural network training algorithms. Though stochastic gradient descent (SGD) and other explicit gradient-based methods are widely adopted, there are still many challenges such as gradient vanish…
In this paper, we study a circle action on a compact oriented manifold with a discrete fixed point set. The fixed point data consists of the weights of the S1-representations at the fixed points. We prove various results and properties of the action, in terms of the fixed point data. We show that the manifold can be…
Critiques incorrect fixed point assertions in digital topology.
problem Incorrect or incorrectly proven fixed point assertions in digital topology.
method Critical review of existing assertions.
result Identifies and critiques incorrect fixed point assertions.
The paper introduces fixed-point centralities for networks and graphons.
problem Defining network centralities for networks and graphons.
method Fixed-point centralities defined via permutation equivariant mappings and graphons.
result Variation bounds of fixed-point centralities under mild assumptions.
Improved convergence of fixed-point methods using windowed Anderson acceleration.
problem Improving convergence of fixed-point methods for symmetric operators.
method Windowed Anderson acceleration for symmetric fixed-point iterations.
result Windowed Anderson acceleration improves convergence over standard fixed-point methods.
A fixed point theorem is proved for inverse transducers, leading to an automata-theoretic proof of the fixed point subgroup of an endomorphism of a finitely generated virtually free group being finitely generated. If the endomorphism is uniformly continuous for the hyperbolic metric, it is proved that the set of regula…
Corrects incorrect assertions about fixed points in digital topology.
problem Incorrect or incorrectly proven assertions about fixed points in digital metric spaces.
method Analysis of existing assertions and proofs.
result Identifies and corrects errors in published assertions.
Paper finds at least 6 fixed points for a specific circle action on a 10D manifold.
problem Finding the minimum number of fixed points for a circle action on a 10D almost complex manifold.
method Established a lower bound by showing the non-existence of a circle action with 4 fixed points.
result There are at least 6 fixed points for a circle action on a 10D compact almost complex manifold.