Research
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.

168,742 papers · 148 categories

Trend · papers per month

143286429572 · Jun 202019922001200920172026
48 results for composite distribution

We establish conditions for compositional generalization in machine learning.

problem Achieving compositional generalization in machine learning models.
method We reformulate compositionality as a property of the data-generating process and derive mild conditions on the training distribution and model architecture.
result Our theoretical framework enables compositional generalization under mild conditions.

New approach for distributed online optimization of non-convex losses with sublinear regret.

problem Regret evaluation and consensus in distributed, multi-agent systems with non-convex losses.
method Composite regret metric and consensus-based online normalized gradient (CONGD) approach for pseudo-convex losses; offline optimization oracle for general non-convex losses.
result First sublinear regret bound for general distributed online non-convex learning.

Energy-based models can generate complex images by combining simpler concepts.

problem Generating natural images that satisfy complex logical combinations of concepts.
method Energy-based models combine probability distributions of simpler concepts to generate compositions.
result Energy-based models can generate images that satisfy conjunctions, disjunctions, and negations of concepts.

Unified theory for neural scaling laws in hierarchically compositional data.

problem Understanding neural scaling laws in hierarchically compositional data.
method Probabilistic context-free grammars and power-law distributed production rules.
result Unified learning curve behavior for classification and next-token prediction tasks.

CFA improves model's ability to generalize across unseen domain-class combinations.

problem Challenges in real-world machine learning applications due to data distribution shifts and limited training data.
method Developed Compositional Feature Alignment (CFA) technique to improve CG ability of pretrained models.
result CFA outperforms common finetuning techniques in compositional generalization.

Paper tackles distributed linear regression with compositional covariates.

problem Solving distributed statistical methodology and computing for massive compositional data.
method Proposes two distributed optimization techniques based on ADMM and CDMM for solving constrained convex optimization problems.
result Established convergence theories for the proposed algorithms under regularity conditions.

This research proves guarantees on sequence models' generalization to longer and novel sequences.

problem Generalization to longer sequences and novel token combinations in sequence models.
method Provable guarantees on length and compositional generalization for various sequence models.
result Limited capacity models achieve both length and compositional generalization with diverse training distributions.

Paper extends FFT-based differential privacy method to heterogeneous compositions.

problem Computing accurate differential privacy guarantees for mixed mechanisms.
method Uses Fast Fourier Transform (FFT) for error analysis and parameter selection.
result Provides tighter bounds for heterogeneous compositions compared to homogeneous cases.

Transformers learn to solve modular arithmetic tasks by in-context learning and skill composition.

problem Understanding how large language models generalize to unseen tasks in modular arithmetic.
method Pre-training on a set of modular arithmetic tasks and evaluating out-of-distribution performance.
result Transformers require two transformer blocks for out-of-distribution generalization, and deeper models exhibit transient out-of-distribution performance.

We consider composite loss functions for multiclass prediction comprising a proper (i.e., Fisher-consistent) loss over probability distributions and an inverse link function. We establish conditions for their (strong) convexity and explore the implications. We also show how the separation of concerns afforded by using …

2012-06-18abs ↗pdf ↗

A folded type model is developed for analyzing compositional data. The proposed model involves an extension of the αα-transformation for compositional data and provides a new and flexible class of distributions for modeling data defined on the simplex sample space. Despite its rather seemingly complex structure, emplo…

2018-02-20abs ↗pdf ↗

OCEAN infers online task identities from context variables.

problem Online task inference for compositional tasks with context adaptation.
method Variational inference framework OCEAN models global and local context variables in a joint latent space.
result OCEAN provides more effective task inference with sequential context adaptation.

Generative Adversarial Networks (GANs) can produce images of remarkable complexity and realism but are generally structured to sample from a single latent source ignoring the explicit spatial interaction between multiple entities that could be present in a scene. Capturing such complex interactions between different ob…

2018-07-19abs ↗pdf ↗

Edgeworth Accountant calculates privacy loss under differential privacy compositions efficiently.

problem Efficiently computing overall privacy loss under composition of private algorithms.
method Analytical approach using ff-differential privacy framework and Edgeworth expansion.
result Non-asymptotic (ε,δ)(ε, δ)-differential privacy bounds with reduced computational cost.

New findings show disentangled latent representations are not enough for robust compositional generalization.

problem Deep learning models struggle with compositional generalization, especially in out-of-distribution samples.
method Investigated a 2D Gaussian generation task with fully disentangled inputs, then forced disentangled latent representations into full-dimensional output space.
result Forcing disentangled latent representations into full-dimensional output space enables robust compositional generalization.

Algorithm samples from composite log-concave distributions using gradient evaluations and restricted Gaussian oracles.

problem Sampling from composite log-concave distributions with limited gradient evaluations.
method Proximal gradient algorithm with RGO for gg and strong/strongly convex conditions for ff.
result Achieves εε error in total variation distance in O~(κdlog4(1/ε))\widetilde{\mathcal O}(κ\sqrt d \log^4(1/ε)) iterations.

Many machine learning models, such as logistic regression~(LR) and support vector machine~(SVM), can be formulated as composite optimization problems. Recently, many distributed stochastic optimization~(DSO) methods have been proposed to solve the large-scale composite optimization problems, which have shown better per…

2016-01-30abs ↗pdf ↗

In this work, we propose a composition/decomposition framework for adversarially training generative models on composed data - data where each sample can be thought of as being constructed from a fixed number of components. In our framework, samples are generated by sampling components from component generators and fee…

2019-01-23abs ↗pdf ↗

Gaussian processes (GPs) are nonparametric priors over functions. Fitting a GP implies computing a posterior distribution of functions consistent with the observed data. Similarly, deep Gaussian processes (DGPs) should allow us to compute a posterior distribution of compositions of multiple functions giving rise to the…

2019-09-17abs ↗pdf ↗

This paper introduces a novel recurrent model for music composition that is tailored to the structure of polyphonic music. We propose an efficient new conditional probabilistic factorization of musical scores, viewing a score as a collection of concurrent, coupled sequences: i.e. voices. To model the conditional distri…

2018-11-20abs ↗pdf ↗

Paper improves privacy bounds for shuffle model using novel numerical techniques.

problem Improving privacy guarantees in the shuffle model of differential privacy.
method Develops and evaluates numerical techniques for tighter (ε,δ)(\varepsilon,δ)-differential privacy bounds.
result Accurately evaluates privacy loss distribution for adaptive compositions of shufflers.

Transformers learn to generalize unseen tasks by composing self-attention layers.

problem How Transformers generalize to unseen, out-of-distribution tasks.
method Examined synthetic examples and pretrained LLMs, focusing on induction heads and latent subspace.
result Transformers can learn hidden rules for unseen tasks by composing self-attention layers, achieving OOD generalization.

This paper presents foundational theoretical results on distributed parameter estimation for undirected probabilistic graphical models. It introduces a general condition on composite likelihood decompositions of these models which guarantees the global consistency of distributed estimators, provided the local estimator…

2014-06-11abs ↗pdf ↗

Estimates returns for dollar cost averaging using geometric Brownian motion.

problem Estimating returns for dollar cost averaging investing strategy.
method Uses geometric Brownian motion and log-Normal distribution to construct a lower bound for returns. Computes parameters recursively and in closed form for dollar cost averaging. Compares to lump sum investing for matching wealth distributions.
result Probability of negative returns is less than 2.5% for 40 years of annual dollar cost averaging.

The paper analyzes the error accumulation in a compositional score-based algorithm for SBI.

problem How to effectively combine multiple observations to improve parameter inference.
method Study of the GAUSS algorithm's compositional score and its mean squared error.
result Established an upper bound on the mean squared error of the compositional score.

There has been remarkable recent work in unpaired image-to-image translation. However, they're restricted to translation on single pairs of distributions, with some exceptions. In this study, we extend one of these works to a scalable multidistribution translation mechanism. Our translation models not only converts fro…

2018-04-16abs ↗pdf ↗

Discriminative classifier for compositional data using hierarchical mixture of Generalized Dirichlet models.

problem Classifying compositional data, especially in spam detection and color space identification.
method Hierarchical mixture of discriminative Generalized Dirichlet classifiers, using variational approximation for parameter learning.
result First time a variational upper-bound for Generalized Dirichlet mixture is proposed in literature.

Study analyzes Airbnb lead-time distributions for Nights Booked and Gross Booking Value, finding divergent shapes and tail behavior.

problem Analyzing lead-time distributions for Airbnb demand metrics.
method Compositional analysis of daily lead-time vectors, fitting Gamma, Weibull, and Lognormal distributions, using generalized Pareto for tail inference.
result Lead-time distributions for Nights Booked and Gross Booking Value diverge, with GBV concentrating more in mid-range horizons.

Agents compose pre-trained policies for complex tasks, improving zero-shot performance.

problem Challenges in long-horizon predictions and estimating visitation distributions induced by policy sequences.
method Learn predictive jumpy world models of multi-step dynamics, enhancing predictions with a consistency objective.
result Compositional planning with jumpy world models yields, on average, a 200% relative improvement over primitive actions on long-horizon tasks.

This paper analyzes how diffusion models learn and generalize concepts.

problem Learning and generalizing concepts in compositional data-generating processes.
method Introduced a structured identity mapping (SIM) task to analyze neural network learning dynamics.
result SIM task captures key empirical observations on compositional generalization.

This paper advances FL algorithms for composite optimization and statistical recovery.

problem Federated learning optimization and statistical recovery in composite settings.
method Proposes Fast Federated Dual Averaging for strongly convex and smooth loss, and Multi-stage Federated Dual Averaging for restricted strongly convex and smooth loss.
result Establishes state-of-the-art iteration and communication complexity, and high probability complexity bound with linear speedup.

A new method estimates rare events using tensor trains.

problem Estimating rare event probabilities in high-dimensional problems.
method Approximating optimal importance distribution via tensor-train decompositions and compositions.
result Better variance reduction and efficient computation of rare event probabilities.

Unified framework for aligning and composing diffusion models to satisfy multiple constraints.

problem Improving quality and compliance of generated samples from diffusion models.
method Constrained optimization framework that unifies alignment and composition of diffusion models.
result Proposed framework effectively satisfies multiple constraints in image generation.

New method for causal inference with complex treatment compositions.

problem Estimating causal effects with compositional treatments.
method Kernel-based covariate functional balancing approach.
result Achieves n\sqrt{n}-consistency without requiring consistent estimation of weights.

Enhances neural networks with prior knowledge through a composite kernel.

problem Lack of effective methods to incorporate prior knowledge into neural networks.
method Integrates a composite kernel combining a neural network kernel and a GP kernel for modeling known properties.
result Demonstrates superior performance and flexibility of the Implicit Composite Kernel (ICK) on synthetic and real-world data.

Paper solves robust convex problems with heavy-tailed noise.

problem Solving convex compositional problems with heavy-tailed noise.
method Sub-Gaussian confidence bounds under weak heavy-tailed noise assumptions, using boosting strategy.
result Achieves nearly optimal high probability convergence result.