This paper shows how path spaces on two-level manifolds can be Hilbert manifold structures.
problem Addressing the structure of path spaces on two-level manifolds.
method Introducing the notion of tameness and constructing charts on path spaces of two-level manifolds.
result Path spaces on tame two-level manifolds have the structure of a Hilbert manifold.
This work analyzes generalization in federated learning using information theory.
problem Generalization performance in federated learning is less explored compared to centralized learning.
method The work applies an information-theoretic analysis via the conditional mutual information (CMI) framework to study federated learning's two-level generalization.
result The work derives multiple CMI-based bounds, including hypothesis-based CMI bounds and fast-rate evaluated CMI bounds, which improve convergence rates for specific model aggregation strategies and structured loss functions.
Paper develops efficient algorithms for robust optimization across multiple groups.
problem Minimizing maximal empirical risk across distinct groups in robust optimization.
method Develops ALEG and ALEM algorithms for two-level finite-sum convex-concave minimax optimization.
result Achieves ε-accuracy with complexity O(m√(nlnm/ε)) and outperforms state-of-the-art methods.
New framework explains why over-parameterized neural networks work well.
problem Why over-parameterized neural networks perform well in practice.
method Neural feature repopulation framework using gradient descent.
result Over-parameterized two-level neural networks learn near optimal feature distributions.
The stochastic variational inference (SVI) paradigm, which combines variational inference, natural gradients, and stochastic updates, was recently proposed for large-scale data analysis in conjugate Bayesian models and demonstrated to be effective in several problems. This paper studies a family of Bayesian latent vari…
This paper examines the valuation of American capped call options with two-level caps. The structure of the immediate exercise region is significantly more complex than in the classical case with constant cap. When the cap grows over time, making extensive use of probabilistic arguments and local time, we show that the…
Paper explores generalization of AID-based bi-level optimization methods.
problem Uncertainty in generalization properties of AID-based bi-level optimization methods.
method Uniform stability analysis and convergence study of AID-based methods.
result AID-based methods can achieve similar generalization as single-level nonconvex problems.
Proposes GST for efficient computation of generalized Sobolev transport on graph metrics.
problem Optimal transport for measures on graph metric spaces with limited flexibility.
method Introduces GST, a generalized variant of Sobolev transport that adapts to various geometric structures.
result GST is significantly faster than Orlicz-Wasserstein (OW) and demonstrates advantages in document classification and topological data analysis.
As a contribution to interpretable machine learning research, we develop a novel optimization framework for learning accurate and sparse two-level Boolean rules. We consider rules in both conjunctive normal form (AND-of-ORs) and disjunctive normal form (OR-of-ANDs). A principled objective function is proposed to trade …
Fast BATLLNN speeds up verification of TLL NNs by 400x.
problem Verifying output constraints for TLL NNs.
method Uses TLL architecture and decoupled box constraints to improve verification performance.
result 400x faster than state-of-the-art verifiers.
Develops a two-level monotonic multistage recommender system for better user-specific prediction.
problem Leveraging user-item-stage dependencies in a monotonic chain of events for enhanced prediction accuracy.
method A multistage recommender system with a two-level monotonic property, using a large-margin classifier based on a nonnegative additive latent factor model.
result The proposed method outperforms existing methods in simulations and an article sharing dataset.
Proposes a method for explaining black-box models with nested feature attributions.
problem Making black-box models transparent and trustworthy.
method Model-agnostic local explanation method exploiting nested feature structure and consistency property.
result Accurate and consistent HiFAs and LoFAs estimated using fewer model queries.
A new method predicts stock ranking uncertainty to improve trading performance during regime shifts.
problem Ranking models fail during regime shifts, leading to suboptimal performance.
method Adapting DEUP to rankers, predicting rank displacement and uncertainty, and proposing a two-level deployment policy.
result The two-level deployment policy improves risk-adjusted performance and indicates DEUP adds value mainly as a tail-risk guard.
This work improves interpretability in deep learning models by introducing a two-level concept discovery framework.
problem High complexity and lack of interpretability in deep learning models, especially for safety-critical tasks.
method Concept Bottleneck Models (CBMs) framework combining vision-language models and data-driven coarse-to-fine concept selection.
result The proposed framework outperforms recent CBM approaches and provides a principled interpretability.
LARF improves random forests with attention mechanisms and contamination models.
problem Improving accuracy in classification tasks with random forests.
method Introduces a two-level attention mechanism and uses a mixture of contamination models.
result Significantly improved classification performance on various datasets.
GraphHull models networks with clear multi-scale explanations of community structure.
problem Lack of self-explainable models in graph machine learning.
method Two-level convex hulls with global archetypes and local prototypes.
result GraphHull models networks with clear multi-scale explanations.
New NN design for nonlinear systems control with guarantees.
problem Designing NN architectures for nonlinear system control with guarantees.
method Exploits system model to design NN architecture, uses TLL NN for approximation.
result Guaranteed NN architecture sufficient for implementing a controller.
In Maslov (2003), a two level model of the occurrence of financial pyramid (bubbles) has been considered. We also considered the mathematical analogy of this model to Bose condensation. In the present paper, we explain why Ponzi schemes and bubbles result in a crisis in real economics. In Maslov (2005), the law of incr…
HyperSAGE learns node representations in hypergraphs without losing information.
problem Learning node representations in hypergraphs is complex due to higher-order relations.
method Two-level neural message passing strategy for accurate information propagation.
result HyperSAGE outperforms state-of-the-art methods on benchmark datasets.
OKDDip uses diverse peers to improve online knowledge distillation.
problem Early saturation in group-based distillation.
method Two-level distillation with multiple auxiliary peers and a group leader, using attention-based aggregation weights.
result OKDDip consistently gives better performance than state-of-the-art approaches.
This work proposes a two-level framework for anomaly detection in sequences using GANs.
problem Detecting anomalies in sequences of discrete elements, especially when they are unknown or rare.
method The approach involves assessing statistics from discriminator layers and building an unsupervised anomaly detection module. GANs are used to augment data and track known data classes.
result The method successfully detects anomalies in sequences of discrete elements, improving detection accuracy and timeliness.
New structure in neural network Hessians explains outliers, improving subspace approximation.
problem Explaining outliers in the spectrum of deepnet Hessians.
method Identified a two-level structure in the Hessian, showing it's not a covariance but a second moment matrix.
result Shows the means of gradients have an additive two-way structure, leading to outliers in the spectrum.
Most research on the interpretability of machine learning systems focuses on the development of a more rigorous notion of interpretability. I suggest that a better understanding of the deficiencies of the intuitive notion of interpretability is needed as well. I show that visualization enables but also impedes intuitiv…
We study the quantum synchronization between a pair of two-level systems inside two coupled cavities. By using a digital-analog decomposition of the master equation that rules the system dynamics, we show that this approach leads to quantum synchronization between both two-level systems. Moreover, we can identify in th…
This paper shows hedging algorithms improve performance in repeated matrix games.
problem Improving multi-agent learning algorithms in repeated matrix games.
method Develops and experiments with hedging algorithms combining a top-level and a set of basic algorithms.
result Well-selected hedging algorithms outperform previous MAL algorithms on repeated matrix games.
Neuro-inspired RL solves complex control problems with fewer controllers.
problem Solving nonlinear control problems with unknown dynamics efficiently.
method Hierarchical RL framework combining limb coordination and reinforcement learning.
result Local LQR controllers combined with a reinforcement learner solve global nonlinear problems.
To answer the existence of optimal swimmer learning/teaching strategies, this work introduces a two-level clustering in order to analyze temporal dynamics of motor learning in breaststroke swimming. Each level have been performed through Sparse Fisher-EM, a unsupervised framework which can be applied efficiently on lar…
A2SGD reduces distributed SGD communication to O(1) per worker.
problem Heavy communication costs in distributed SGD for large models.
method Two-level gradient averaging to consolidate gradients to two local averages.
result Achieves O(1) communication complexity per worker, significantly reducing traffic and training time.
The paper designs neural networks with assurance for controlling nonlinear systems.
problem Designing neural networks with assurance for nonlinear system control.
method Bounding the number of affine functions needed for a CPWA function, connecting it to a TLL NN architecture.
result The TLL NN architecture is parameterized by the number of affine functions in the CPWA function it realizes.
This paper shows overparameterized deep neural networks are convex and learn useful features.
problem Analyzing fully trained overparameterized deep neural networks.
method Generalized neural feature repopulation technique.
result Overparameterized deep neural networks are inherently convex and learn useful features.
Recently ({\em Class. Quant. Grav.} {\bf 20} 625-664) the concept of {\em causal mapping} between spacetimes --essentially equivalent in this context to the {\em chronological map} one in abstract chronological spaces--, and the related notion of {\em causal structure}, have been introduced as new tools to study causal…
Polynomial-time reachability for LTI systems with TLL NN controllers is achieved.
problem Bounding the reachable set of LTI systems controlled by TLL NN controllers.
method Polynomial-time computation of exact one-step reachable set and tight bounding box via two methods.
result Exact reachability computation in polynomial time for TLL NN controllers.
FedDAG learns DAG structures from decentralized data.
problem Learning DAG structures from private decentralized data.
method Gradient-based framework with two-level structures.
result FedDAG learns DAG structure without direct data sharing.
VTA offers flexible DL specialization for evolving workloads.
problem Inflexible specialized DL hardware accelerators.
method Parametrizable architecture, two-level ISA, JIT compiler.
result Flexible deep learning specialization on edge-class FPGAs.
Deep latent-variable models learn representations of high-dimensional data in an unsupervised manner. A number of recent efforts have focused on learning representations that disentangle statistically independent axes of variation by introducing modifications to the standard objective function. These approaches general…
A theorem connects integral of second-order derivatives to function rise.
problem Understanding the integral of second-order derivatives over regions.
method Proves integral proportional to function rise over specified regions.
result Integral of second-order derivatives equals rise in function value.
Paper introduces a new distributional successor measure for reinforcement learning.
problem Learning the distributional consequences of behavior in reinforcement learning.
method Formulates distributional successor measure as a distribution over distributions, proposes algorithm to learn it from data.
result Demonstrates zero-shot risk-sensitive policy evaluation.
Proposes a new method for multivariate functional regression.
problem Multivariate functional regression with complex relationships.
method Nested reduced-rank regularization (NRRR) approach.
result Consistent and effective in fitting multivariate functional regression models.
BILBO optimizes bilevel problems without repeated lower-level optimizations.
problem Challenges in bilevel optimization, especially in noisy, constrained, and derivative-free settings.
method BILevel Bayesian Optimization (BILBO) that optimizes both levels simultaneously, using confidence-bounds and function query selection.
result Theoretical and empirical evidence of BILBO's effectiveness on various problems.
HML improves meta learning for diverse tasks.
problem Few-shot learning with heterogeneous tasks.
method Hierarchical factorization and dual-level training.
result HML outperforms existing methods in generalization.
Selective prediction framework reduces errors in molecular structure identification from MS/MS.
problem High-stakes applications require reliable molecular structure identification from MS/MS data.
method Selective prediction framework using risk-coverage tradeoff and uncertainty quantification.
result First-order confidence measures and retrieval-level aleatoric uncertainty achieve strong risk-coverage tradeoffs.
Genome-wide association studies (GWA studies or GWAS) investigate the relationships between genetic variants such as single-nucleotide polymorphisms (SNPs) and individual traits. Recently, incorporating biological priors together with machine learning methods in GWA studies has attracted increasing attention. However, …
New method controls linear systems with partial info and disturbances.
problem Controlling linear dynamical systems under partial observation and adversarial disturbances.
method Double Spectral Control (DSC) using two-level spectral approximation strategy.
result Matches best known regret guarantees with exponential runtime improvement.
A VAE model predicts material properties and microstructures.
problem Building forward and inverse structure-property linkages in materials science.
method Combines VAE with regression, using a two-level prior and multi-modal Gaussian mixture.
result The model achieves accurate forward and inverse predictions of material properties and microstructures.
The paper compares multi-fidelity methods for Gaussian process surrogates in physics.
problem Limited availability of data due to expensive simulations.
method Extending non-linear autoregressive methods to multi-fidelity models and incorporating delay terms.
result Multi-fidelity methods generally have smaller prediction error for the same computational cost.
This paper deals with prediction of anopheles number, the main vector of malaria risk, using environmental and climate variables. The variables selection is based on an automatic machine learning method using regression trees, and random forests combined with stratified two levels cross validation. The minimum threshol…
HPPCA improves imputation of longitudinal data with missing values.
problem Handling incomplete, high-dimensional longitudinal data with nested sources of variation and temporal dependency.
method Hierarchical probabilistic principal component analysis (HPPCA) with a two-level latent factor model and Gaussian process.
result HPPCA outperforms standard PPCA and multivariate functional PCA in imputation accuracy, even under heavy missingness and model misspecification.
Model interpretability is a requirement in many applications in which crucial decisions are made by users relying on a model's outputs. The recent movement for "algorithmic fairness" also stipulates explainability, and therefore interpretability of learning models. And yet the most successful contemporary Machine Learn…