New framework identifies strongly identifiable models from flexible generators.
problem Indeterminacies in generative models that prevent unique latent codes.
method Theoretical framework for analyzing latent variable models, excluding certain indeterminacies.
result Strong identifiability possible even with flexible nonlinear generators.
The paper explores strong identifiability and parameter learning in regression models with heterogeneous responses.
problem Understanding heterogeneity in data populations through conditional distributions of a response variable.
method Investigation of strong identifiability, convergence rates, and posterior contraction behavior in finite mixture of regression models.
result Theoretical findings on conditions for strong identifiability and rates of convergence in regression mixture models.
Paper analyzes weak-to-strong generalization in CNNs, identifying data-scarce and data-abundant regimes.
problem Weak-to-strong generalization in CNNs trained on weak models.
method Formal analysis of gradient descent dynamics in data-scarce and data-abundant regimes.
result Identifies two regimes and distinct mechanisms of generalization in each.
RAVEN improves weak-to-strong generalization under distribution shifts.
problem Weak models fail to supervise strong models effectively under distribution shifts.
method RAVEN dynamically learns optimal combinations of weak models and strong model parameters.
result RAVEN outperforms existing methods by over 30% on out-of-distribution tasks.
Kernel method improves instrumental variable regression rates.
problem Nonparametric instrumental variable regression with weak instruments.
method Kernel-based two-stage least-squares method, strong L2 convergence analysis. result Minimax optimal rates for instrumental regression under standard assumptions.
New model shows weak teachers can help strong students learn even with imperfect labels.
problem Improving strong student's performance with weak teacher's imperfect pseudolabels.
method Stylized overparameterized spiked covariance model with Gaussian covariates, proving two phases of generalization.
result Provable successful and random guessing phases of strong student's generalization.
Optimized parallel algorithms for identifying strong ties in data.
problem Identifying strong ties in data with varying distances and community sizes.
method Design and analysis of sequential and parallel algorithms for partitioned local depths.
result Optimized algorithms achieve up to 19.4x speedup in parallel execution.
New method identifies latent variables without strong assumptions.
problem Recovering latent variables from observational data without strong assumptions.
method Diverse dictionary learning, using set-theoretic intersections, complements, and symmetric differences.
result Identifiability of latent variables up to appropriate indeterminacies without strong assumptions.
The study explores the strengths and weaknesses of models that generalize from weak to strong supervision.
problem Understanding the limitations and capabilities of models that generalize from weak to strong supervision.
method Theoretical analysis and experimental validation in both classification and regression settings.
result Theoretical bounds reveal the importance of strong generalization and calibration of the weak model and a careful balance in the training process.
TAMD prevents degeneracy in finite mixtures, offering strong guarantees but modest practical improvements.
problem Degeneracy in maximum likelihood estimation of finite mixtures.
method Transcendental regularization with analytic barrier functions.
result Strong theoretical guarantees (identifiability, consistency, robustness) but modest practical improvements.
We identify higher-charge configurations that satisfy Euler-Lagrange equations for the (strong coupling limit of) Faddeev-Hopf model, by means of adequate changes of the domain metric and a reduction technique based on α-Hopf construction. In the last case it is proved that the solutions are local minima for the redu…
Study proves stability of big bang singularity in complex system.
problem Stability of Kasner solutions in Einstein-Maxwell-scalar field-Vlasov system.
method Detailed mathematical structures and new delicate arguments.
result Nonlinear stability with Kasner exponents in full strong sub-critical regime.
New method for inference on strongly identified functionals even when nuisance functions are weakly identified.
problem Inference on continuous linear functionals of weakly identified nuisance functions defined by conditional moment restrictions.
method Proposes penalized minimax estimators for both the primary and debiasing nuisance functions, which can converge to fixed limits regardless of nuisance identifiability.
result Proves the asymptotic normality of a debiased estimator for the functional of interest, leading to asymptotically valid confidence intervals.
New insights connect strong coupling SYM amplitudes to hyperkähler geometry.
problem Understanding strong coupling SYM amplitudes.
method Integrable systems, pseudo-hyperkähler geometry, twistor theory.
result Remainder function is a pseudo-Kähler scalar in hyperkähler geometry.
This paper explores formal verification for autonomous systems, identifying limitations and proposing improvements.
problem Ensuring safety of autonomous systems like self-driving cars and drones.
method Formal verification techniques based on formal methods, analyzing three assumptions and their limitations.
result Preliminary work to improve the strength of evidence provided by formal verification.
New method identifies latent components in PNL mixtures without strong assumptions.
problem Identifying latent components in PNL mixtures under unknown nonlinear functions.
method Carefully designed UML criterion to identify a null space associated with the mixing system.
result Identification/removal of unknown nonlinearity under minimal conditions.
CB-SLICE identifies concept-based error slices in deep learning models.
problem Systematic errors in deep learning models on specific groups.
method Concept Bottleneck Models (CBMs) and concept representations.
result CB-SLICE outperforms state-of-the-art methods in error slice identification.
We identify a strong stability condition on minimal submanifolds that implies uniqueness and dynamical stability properties. In particular, we prove a uniqueness theorem and a C^1 dynamical stability theorem of the mean curvature flow for minimal submanifolds that satisfy this condition. The latter theorem states that …
We embed arbitrary groups into regular graphs with prescribed automorphisms.
problem Embedding arbitrary groups into regular graphs with specific automorphisms.
method Constructing regular graphs with strong embeddings and automorphism groups isomorphic to any given finite group.
result For every d≥3 and every finite group G, there exists a d-regular graph Γ with a strong embedding β such that Aut(Γ)≅Aut(β(Γ))≅G. We solve continuous-time latent SDE identifiability using diffusion shifts.
problem Identifiability of latent SDEs in continuous-time time series.
method Environment-induced shifts in diffusion covariance for additive-noise latent SDEs.
result Two diagonal diffusion regimes with distinct variance ratios identify latent coordinates up to permutation and scaling.
Investigates least squares estimation in deterministic MoE models.
problem Complexity and difficulty in analyzing MoE models.
method Least squares estimation under deterministic MoE models.
result Rates of estimating strongly identifiable experts are faster than polynomial experts.
In this paper we develop a methodology to analyze and compare multiple global networks. We focus our analysis on the relation between human migration and trade. First, we identify the subset of products for which the presence of a community of migrants significantly increases trade intensity. To assure comparability ac…
New method identifies causal relationships from interventions in complex systems.
problem Learning causal representations from unknown, latent interventions with general nonlinear mixing.
method Strong identifiability results with unknown single-node interventions, using geometric structure of transformed data.
result First instance of causal identifiability from non-paired interventions for deep neural network embeddings.
New algorithm achieves strong consistency in binary non-uniform hypergraph classification.
problem Node classification on binary non-uniform hypergraphs with varying edge probabilities.
method Proposes a refinement algorithm using power iteration on weighted adjacency matrices.
result Proves optimality of the refinement algorithm, achieving strong consistency and IT lower bound.
This paper studies directed exploration for reinforcement learning agents by tracking uncertainty about the value of each available action. We identify two sources of uncertainty that are relevant for exploration. The first originates from limited data (parametric uncertainty), while the second originates from the dist…
Improved machine learning models outperform their simpler counterparts by using imperfect labels.
problem Improving model performance using imperfect labels.
method Random feature ridge regression (RFRR) with a deterministic equivalent for excess test error.
result The student model can outperform the teacher model regardless of the teacher's scaling law, achieving the minimax optimal rate.
Paper develops a framework to identify latent dynamics from high-dimensional data.
problem Identifying latent dynamics from high-dimensional time-series data.
method Combines physics inductive bias and learn-to-identify strategy.
result Meta-HyLaD framework effectively identifies hybrid latent dynamics.
Relationship lending is broadly interpreted as a strong partnership between a lender and a borrower. Nevertheless, we still lack consensus regarding how to quantify the strength of a lending relationship, while simple statistics such as the frequency and volume of loans have been used as proxies in previous studies. He…
Learning the directed acyclic graph (DAG) structure of a Bayesian network from observational data is a notoriously difficult problem for which many hardness results are known. In this paper we propose a provably polynomial-time algorithm for learning sparse Gaussian Bayesian networks with equal noise variance --- a cla…
New approach identifies latent properties from mechanisms, not just data.
problem Identifying latent properties from data generating processes.
method Equivariance perspective on identifiable representation learning.
result Identification of latent properties is possible up to shared equivariances in known mechanisms.
New tests for identifying the number of latent factors in short panels with small time dimensions.
problem Determining the number of latent factors in short panels with small time dimensions.
method Eigenvalue tests based on variance-covariance matrices of asset returns, with assumptions on spherical errors or instrumental variables for factor betas.
result Established asymptotic distributional results and proposed a novel statistical test for weak factors.
Identifies root causes of outliers in unknown cyclic graphs.
problem Outliers in unknown cyclic graphs with linear structural equations.
method Identifies a short list of potential root causes based on strong perturbation and structural equations.
result The shortlist includes true root causes and their parents on the cycle.
New method exploits independence in instrumental variable models for better causal inference.
problem Identify causal functions in the presence of unobserved confounders.
method HSIC-X method that exploits independence between response, hidden confounders, and instruments.
result The method provides better finite sample results and is invariant to distributional shifts.
Differentiable structure learning addresses DAGs with multiple global minimizers.
problem Identify the true DAG from global minimizers of acyclicity-constrained optimization problems.
method Carefully regularize the likelihood to identify the sparsest model in the Markov equivalence class.
result Regularization of the likelihood defines a score that identifies the sparsest model in general models and likelihoods.
The study identifies extremal dependence in financial markets using a bootstrap-based testing procedure.
problem Accurately identifying extremal dependence in multivariate heavy-tailed financial data.
method Bootstrap-based testing procedure applied to U.S. and Chinese stock returns.
result The U.S. exhibits more isolated clustering of dependent assets compared to China.
New method identifies causal relationships without strong assumptions.
problem Causal Representation Learning (CRL) is ill-posed due to representation and causal discovery issues.
method Identifiability based on grouping of observational variables, self-supervised estimation framework.
result Practical identifiability conditions without temporal structure, interventions, or weak supervision.
To identify emerging interdependencies between traded stocks we investigate the behavior of the stocks of FTSE 100 companies in the period 2000-2015, by looking at daily stock values. Exploiting the power of information theoretical measures to extract direct influences between multiple time series, we compute the infor…
Two machine learning methods detect insider trading from investor activity data.
problem Detecting insider trading from trading activity data is challenging.
method Two unsupervised machine learning methods: clustering and group identification.
result Identifies potential insider trading rings around price sensitive events.
Post-detection analysis identifies responsible coordinates for multivariate change-points.
problem Identifying which coordinates in multivariate time series change after a detected change-point.
method Two-sample testing procedures with nonparametric tests for Type I error control.
result Strong performance of proposed post hoc statistical procedures.
Identifying anomalous patterns in real-world data is essential for understanding where, when, and how systems deviate from their expected dynamics. Yet methods that separately consider the anomalousness of each individual data point have low detection power for subtle, emerging irregularities. Additionally, recent dete…
Boosting improves accuracy with fewer calls to weak learners for certain concept classes.
problem Improving accuracy of learning algorithms with limited weak learner calls.
method Combines boosting and list-decodable codes to achieve better performance for specific concept classes.
result A new boosting algorithm that achieves strong learning with fewer calls to weak learners and additional samples.
New framework for identifying spatial data components using TP latent components.
problem Identifying complex dependencies in spatial data.
method Introduces a new nonlinear ICA framework with t-process latent components and develops a learning and inference algorithm. result Identifiability of TP independent components under general conditions and Gaussian Process limit.
Unified framework for best arm identification and dueling bandits regret minimization.
problem Best arm identification and dueling bandits regret minimization.
method Tree-Guided Identify-Then-Exploit (TG-ITE) framework.
result Unified approach achieving optimal sample complexity and regret guarantees.
Boosted Control Functions improve prediction under distributional shifts.
problem Prediction under distributional shifts in the presence of hidden confounding.
method Boosted Control Function (BCF) and ControlTwicing algorithm.
result BCF allows for distribution generalization and invariance under nonlinear, non-identifiable structural functions.
LANCA uses ANM to learn latent causal factors without supervision.
problem Learning latent causal factors without supervision.
method LANCA employs a deterministic Wasserstein Auto-Encoder coupled with a differentiable ANM Layer.
result LANCA outperforms baselines on physics and photorealistic environments.
Proposes a regularization approach to model German power derivative market, identifying significant risk spillovers.
problem Large portfolio of German power derivative contracts, identifying significant risk spillovers.
method Combines high-dimensional variable selection with dynamic network analysis.
result Identifies significant risk contributors and interdependencies between contracts, especially spot contracts.
The purpose of this paper is to introduce a concept of equivalence between machine learning algorithms. We define two notions of algorithmic equivalence, namely, weak and strong equivalence. These notions are of paramount importance for identifying when learning prop erties from one learning algorithm can be transferre…
New framework TDRL identifies latent causal variables from sequential data.
problem Identify latent causal variables from sequential data.
method Proposes TDRL framework to recover time-delayed latent causal variables and identify their relations from measured sequential data.
result Identifies latent causal variables reliably from sequential data.