Sequence-to-sequence models with soft attention have been successfully applied to a wide variety of problems, but their decoding process incurs a quadratic time and space cost and is inapplicable to real-time sequence transduction. To address these issues, we propose Monotonic Chunkwise Attention (MoChA), which adaptiv…
On-device research index
arXiv research
A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
168,695 papers · 148 categories
Trend · papers per month
48 results for “monotone sequences”
The paper tackles online learning problems with monotone arm sequences, achieving optimal or near-optimal regret bounds.
problem Online learning problems with ordinal and monotone arm sequences, such as dynamic pricing and clinical trials.
method Proposes algorithms for continuum-armed bandit problems with monotone arm sequences, achieving optimal or near-optimal regret bounds.
result Achieves optimal or near-optimal regret bounds for monotone arm sequences, differing from the continuous-armed bandit literature.
Holonomy groups of metric connections converge in a monotonic way.
problem Monotonicity of holonomy groups under convergence of metric connections.
method Proving the monotonicity of holonomy groups for sequences of metric connections converging in .
result The holonomy group of the limit connection is contained in the holonomy group of the initial connections.
Proves existence of planar curves with specific curvature.
problem Existence of planar closed curves with prescribed curvature.
method Variational methods, adding a parameter, monotonicity trick.
result Existence of planar closed curves with prescribed curvature for some curvature functions.
We define an integer graded symplectic Floer cohomology and a spectral sequence which are new invariants for monotone Lagrangian sub-manifolds and exact isotopies. Such an integer graded Floer cohomology is an integral lifting of the usual Floer-Oh cohomology with $Z_{\Si (L)}$ grading. As one of applications of the sp…
Unimodal sequences of moves connect 3-manifold triangulations.
problem Understanding the structure of sequences of bistellar flips.
method Examined unimodal sequences of moves that increase and decrease triangulation size.
result Proved that any two one-vertex triangulations are connected by a unimodal sequence of moves.
New method learns low-dimensional representations of nonlinear time series without supervision.
problem Learning low-dimensional representations of nonlinear time series without supervision.
method Based on monotone variational inequality, the method learns representations by assuming sequences arise from a common domain.
result The method can learn the geometry for the entire domain and faithful representations for the dynamics of each individual sequence.
Single-timescale analysis improves convergence in multi-sequence stochastic approximation.
problem Finite-time convergence of nonlinear stochastic approximation with multiple coupled sequences.
method Smoothness property of fixed points and analysis of fine-grained single-timescale SA.
result Improved iteration complexity for achieving ε-accuracy in multi-sequence single-timescale SA.
Let C_n(M) be the configuration space of n distinct ordered points in M. We prove that if M is any connected orientable manifold (closed or open), the homology groups H_i(C_n(M); Q) are representation stable in the sense of [Church-Farb]. Applying this to the trivial representation, we obtain as a corollary that the un…
We define an integer graded symplectic Floer cohomology and a Fintushel-Stern type spectral sequence which are new invariants for monotone Lagrangian sub-manifolds and exact isotopes. The Z-graded symplectic Floer cohomology is an integral lifting of the usual Z_Sigma(L)-graded Floer-Oh cohomology. We prove the Kunneth…
Floer homotopy theory applies to Lagrangians, overcoming curvature issues.
problem Curvature phenomena in high dimensions for monotone Lagrangians.
method Introduces -truncated, -oriented flow categories and module prospectrum.
result Well-defined invariants for closed embedded monotone Lagrangians.
This paper analyzes and improves monotonic accelerated algorithms like M-NAG and M-FISTA.
problem Establishing linear convergence of M-NAG and M-FISTA under strong convexity.
method Lyapunov analysis and modified Lyapunov functions.
result Linear convergence of M-NAG and M-FISTA is guaranteed without full NAG iterates.
In this paper, we establish a general monotonicity formula of the following elliptic system $$ Δu_i+f_i(u_1,...,u_m)=0 \quad {\rm in} Ω, \label{0.1} $$ where is a bounded domain, , and is a given smooth function of …
Framework for online resource allocation using social welfare functions.
problem Optimal allocation of resources over time steps in a population.
method Confidence sequence framework for SWF-based online learning and inference, valid for any monotonic, concave, and Lipschitz-continuous SWF.
result Achieves near-optimal regret of for SWF-agnostic algorithm SWF-UCB.
Study online monotone density estimation with expert aggregation and log-optimal calibration.
problem Online monotone density estimation and log-optimal calibration.
method Proposed two online estimators: Grenander estimator and expert aggregation estimator.
result Online estimators achieve cumulative log-likelihood gap and pathwise regret bound.
New algorithms avoid non-monotonic risk curves in statistical learning.
problem Non-monotonic behavior of risk curves in statistical learning.
method Derive risk-monotonic algorithms under weak assumptions.
result Risk monotonicity does not necessarily lead to worse excess risk rates.
Investigates probability of error in structured thresholding bandit problems.
problem Probability of misclassifying arms in structured thresholding bandit problems.
method Analyzes two shape constraints: monotonic increasing and concave sequences of arm means.
result Upper and lower bounds for the probability of error match up to constants in the problem dependent regime.
In this paper, we consider first-order convergence theory and algorithms for solving a class of non-convex non-concave min-max saddle-point problems, whose objective function is weakly convex in the variables of minimization and weakly concave in the variables of maximization. It has many important applications in mach…
This note has an experimental nature and contains no new theorems. We introduce certain moves for classical knot diagrams that for all the very many examples we have tested them on give a monotonic complete simplification. A complete simplification of a knot diagram D is a sequence of moves that transform D into a diag…
Traditional pairwise sequence alignment is based on matching individual samples from two sequences, under time monotonicity constraints. However, in many application settings matching subsequences (segments) instead of individual samples may bring in additional robustness to noise or local non-causal perturbations. Thi…
The paper studies convergence of cosmological spacetimes using null distance.
problem Convergence of cosmological spacetimes with compact slices.
method Using null distance and Gromov-Hausdorff convergence, the paper establishes convergence results for spacetimes with mild extension properties.
result Uniform convergence of null distances and Gromov-Hausdorff convergence for monotone sequences of spacetimes.
Undirected neural sequence models such as BERT (Devlin et al., 2019) have received renewed interest due to their success on discriminative natural language understanding tasks such as question-answering and natural language inference. The problem of generating sequences directly from these models has received relativel…
Study de Rham homomorphism for Lipschitz cohomologies on metric simplicial complexes.
problem Triviality of de Rham homomorphism kernel and non-increasing monotonicity of parameters.
method Regularization in Lipschitz de Rham calculus on metric simplicial complexes with bounded geometry.
result Explicit specification of non-trivial cohomology classes for a sequence of parameters.
In this paper, we present Neural Phrase-based Machine Translation (NPMT). Our method explicitly models the phrase structures in output sequences using Sleep-WAke Networks (SWAN), a recently proposed segmentation-based sequence modeling method. To mitigate the monotonic alignment requirement of SWAN, we introduce a new …
We analyze the signature type of a cascade of periodic orbits associated to period doubling renormalizable maps of the two dimensional disk. The signature is a sequence of rational numbers which describes how periodic orbits turn each other and is invariant by topological conjugacies that preserve orientation. We prove…
This paper studies rapidly forming singularities in the Yang-Mills flow. It is shown that a sequence of blow-ups near the singular point converges, modulo the gauge group, to a homothetically shrinking soliton with non-zero curvature. The proof uses Hamilton's monotonicity formula. Examples of homothetically shrinking …
New analysis of annealing paths in sampling and estimation.
problem Sampling from complex distributions and estimating normalization constants.
method Extending known results on Bregman divergence to quasi-arithmetic means under monotonic embedding.
result Analogous result for quasi-arithmetic means, highlighting the interplay between means, parametric families, and divergence functionals.
Adaptive learning rate improves FTRL's performance in online learning.
problem Optimizing FTRL's learning rate for competitive regret in online learning.
method Formulated as a sequential decision-making problem, introduced competitive analysis framework, and proposed stability-penalty matching update rules.
result Achieved a constant competitive ratio under specific conditions, enabling Best-Of-Both-Worlds algorithms.
We propose a new framework for how to use sequential Monte Carlo (SMC) algorithms for inference in probabilistic graphical models (PGM). Via a sequential decomposition of the PGM we find a sequence of auxiliary distributions defined on a monotonically increasing sequence of probability spaces. By targeting these auxili…
In this paper we consider a general matrix factorization model which covers a large class of existing models with many applications in areas such as machine learning and imaging sciences. To solve this possibly nonconvex, nonsmooth and non-Lipschitz problem, we develop a non-monotone alternating updating method based o…
This paper presents some partial answers to the following question. QUESTION. If a normal space X is the union of an increasing sequence of open sets U(1), U(2), U(3) ... such that each U(n) contracts to a point in X, must X be contractible? The main results of the paper are: THEOREM 1. If a normal space X is the union…
Meta-learning improves event prediction from short sequences.
problem Predicting events from short sequences is challenging.
method Meta-learning approach using recurrent neural networks and monotonic neural networks.
result Meta-learning enhances long-term prediction performance.
The paper examines sequences of metric spaces converging to compact limits with specific properties.
problem Understanding convergence of metric spaces with compact limits.
method Analyzes sequences of metric spaces with increasing distance functions and uniform bounds, proving convergence under certain conditions.
result Uniform and Gromov-Hausdorff convergence and volume preserving intrinsic flat convergence to compact limits.
Graph Shift (GS) algorithms are recently focused as a promising approach for discovering dense subgraphs in noisy data. However, there are no theoretical foundations for proving the convergence of the GS Algorithm. In this paper, we propose a generic theoretical framework consisting of three key GS components: simplex …
A key problem in reinforcement learning for control with general function approximators (such as deep neural networks and other nonlinear functions) is that, for many algorithms employed in practice, updates to the policy or -function may fail to improve performance---or worse, actually cause the policy performance …
Optimizes profit in targeted marketing across multiple markets with varying marketing expenditures.
problem Maximizing profit in a sequential marketing strategy with multiple markets and varying marketing costs.
method Near-optimal algorithms in an adversarial bandit setting, proving regret bounds for different demand curve types.
result Proved near-optimal regret bounds for the profit-maximization problem in targeted marketing.
Conformer encoder reverses sequence in time dimension, affecting decoder training.
problem Reversal of sequence in Conformer encoder impacts decoder training.
method Analyzed initial behavior of decoder cross-attention and proposed methods to avoid flipping.
result Self-attention module of Conformer starts dominating, allowing only reversed information to pass.
The paper addresses monotonicity in machine learning models for fairness and accountability.
problem Ensuring fairness and accountability in transparent machine learning models.
method Study of three types of monotonicity (individual, weak pairwise, strong pairwise) and propose monotonic groves of neural additive models.
result Monotonic groves of neural additive models maintain transparency, accountability, and fairness.
Bayesian approach improves online prediction accuracy without distributional assumptions.
problem Online construction of confidence sets for black-box models.
method Combines empirical distribution with Bayesian regularization to predict quantiles.
result Adaptive algorithm with low regret and correct coverage probability for iid data.
We investigate a class of quadratic-exponential growth BSDEs with jumps. The quadratic structure introduced by Barrieu & El Karoui (2013) yields the universal bounds on the possible solutions. With local Lipschitz continuity and the so-called A_gamma-condition for the comparison principle to hold, we prove the existenc…
Paper develops an online covariance estimator for nonsmooth stochastic approximation problems.
problem Estimating covariance in nonsmooth, potentially non-monotone settings.
method Online batch-means covariance matrix estimator.
result Estimator achieves convergence rate of .
Probit Monotone BARTstat.ML
Probit Monotone BART estimates binary outcomes using monotonic functions.
problem Estimating conditional mean functions for binary outcomes with monotonicity constraints.
method Proposes a new BART variant that incorporates monotonicity constraints for binary outcomes.
result Allows for more precise estimation of monotonic functions in binary outcome models.
Study uses instanton Floer theory to obstruct knot unknotting operations.
problem Obstructing knot unknotting operations and ribbon concordance.
method Equivariant singular instanton Floer theory with Chern--Simons filtration.
result For a large class of slice knots, any unknotting sequence must contain both signs.
Monotone neural networks can approximate and interpolate functions efficiently.
problem Understanding the efficiency and expressiveness of monotone neural networks.
method Solving the monotone interpolation problem using depth-4 networks and comparing size bounds with arbitrary networks.
result Monotone neural networks can approximate and interpolate functions efficiently, but may require exponential size in high dimensions.
The Schwarz lemmas are well-known characterizations for holomorphic maps and we exhibit two examples of their applications. For a sequence family of biholomorphisms , it is useful to determine the location of for a fixed point in source manifolds (see Proposition \ref{2.5}). With it, we extend the For…
Probabilistic models are a critical part of the modern deep learning toolbox - ranging from generative models (VAEs, GANs), sequence to sequence models used in machine translation and speech processing to models over functional spaces (conditional neural processes, neural processes). Given the size and complexity of th…
Improves k-NN for monotonic data with robustness against noise.
problem Class noise in real-life data violates monotonic constraints in k-NN.
method Monotonic Fuzzy k-NN (MonFkNN) with new fuzzy membership calculation.
result Significant accuracy improvements and robustness against monotonic noise.
Study examines explainable machine learning for monotonic models, finding Integrated gradients better for strong monotonicity.
problem Applying explainable machine learning to science-informed models.
method Proposed axioms for monotonicity, tested Shapley value and Integrated gradients methods.
result Integrated gradients provides better explanations for strong monotonicity.