We improve robust parameter estimation in causal models from observational data.
problem Robustly estimating parameters in linear structural equation models from observational data.
method Extending Sankararaman et al. (2019) to a broader class of models, providing sufficient conditions for robust identifiability.
result For a large set of parameters, robust identifiability holds and existing algorithms achieve robust identifiability.
Study shows not all ML models are uniquely identifiable from data.
problem Identifiability issues in machine learning models.
method Investigated through a case study on gait dynamics using a bipedal-spring mass model.
result Some parameters can be identified, but others remain unidentifiable.
Conditions for uniquely identifying parameters of deep ReLU networks.
problem Characterizing networks whose parameters can be uniquely identified.
method Conditions on deep fully-connected feedforward ReLU neural networks.
result Parameters of the network are uniquely identified under certain conditions.
GENNI visualises neural network symmetries for better identifiability.
problem Identifying functionally equivalent parameters in neural networks.
method Proposes GENNI, an algorithm to efficiently visualise equivalence classes.
result Allows better exploration of identifiability questions in neural networks.
Analysis of DPPs and k-DPPs via spectral decomposition reveals identifiable parameters and non-identifiability gaps.
problem Identifying parameters of DPPs and k-DPPs through spectral decomposition.
method Spectral decomposition of the covariance matrix, analysis of invariances, and counting arguments.
result Identifiability of parameters changes fundamentally for k-DPPs, with specific invariances and non-identifiability gaps.
Hypothesis testing in singular models is fundamentally about identifiable vs. non-identifiable parameters.
problem Testing in singular models is inherently problematic due to non-identifiability and degeneracy of Fisher information.
method Formalized the overlap obstruction and showed that hypotheses over non-identifiable parameters are untestable, while those over identifiable parameters reduce to classical testing.
result Hypotheses over non-identifiable parameters are untestable, while those over identifiable parameters reduce to classical testing.
Overparametrized neural networks retain significant epistemic uncertainty even with sufficient data.
problem Epistemic uncertainty in overparametrized neural networks persists despite model identifiability.
method Analysis of non-identifiability and characterization of residual uncertainty in one-hidden-layer ReLU networks.
result Substantial parameter uncertainty remains even when the underlying function is fully identified.
New method identifies causal parameters in tree-shaped linear models using cycles.
problem Identifying causal parameters from correlations in tree-shaped linear models.
method Investigates tree-shaped linear models, uses missing cycles to identify causal parameters, solves quadratic equations.
result Shows how missing cycles can be combined to obtain a unique solution for causal parameters.
Latent feature models (LFM)s are widely employed for extracting latent structures of data. While offering high, parameter estimation is difficult with LFMs because of the combinational nature of latent features, and non-identifiability is a particularly difficult problem when parameter estimation is not unique and ther…
New method improves neural network robustness by identifying functions rather than parameters.
problem Neural networks' lack of robustness to distribution shifts.
method Identify the function represented by quadratic networks, not their parameters.
result Obtain robust generalization bounds for neural networks.
New method uses logical relations to derive bounds and inequality constraints from causal models.
problem Recovering bounds and inequality constraints from unobserved confounding.
method Using rules of probability and restrictions on counterfactuals implied by causal graphical models.
result Powerful method to recover known and novel bounds and constraints.
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.
APD method decomposes neural network parameters into simple, faithful components.
problem Understanding the internal mechanisms learned by neural networks.
method Attribution-based Parameter Decomposition (APD) method.
result Demonstrated effectiveness in recovering features, separating computations, and identifying representations.
Researchers show mixtures of ranking models are generally identifiable.
problem Understanding when and how parameters of mixtures of ranking models can be uniquely determined.
method Algebraic geometry framework applied to verify the number of solutions in polynomial systems.
result Popular mixtures of ranking models with two components are generically identifiable.
Paper proves identifiability and consistency of hub model for network inference.
problem Identifying network structure from group behavior.
method Hub model and variants, proving identifiability and consistency under mild conditions.
result Identifiability and estimation consistency of hub model and its variants proved.
The paper shows that certain learned representations are identifiable in function space.
problem Identifiability of learned representations in deep neural networks.
method Using recent advances in nonlinear ICA, the paper shows that a large family of discriminative models are identifiable in function space, up to a linear indeterminacy.
result Many models for representation learning are identifiable in function space, including text, images, and audio.
Determining how to appropriately select the tuning parameter is essential in penalized likelihood methods for high-dimensional data analysis. We examine this problem in the setting of penalized likelihood methods for generalized linear models, where the dimensionality of covariates p is allowed to increase exponentiall…
New lens on self-supervised learning: parameter identifiability.
problem Identifying good features for downstream tasks in self-supervised learning.
method Consider data from a parametric probabilistic model, train a predictor, and ask if ground truth parameters can be read off the optimal predictor.
result Some prediction tasks yield identifiability, others do not, revealing a rich landscape.
KOMET identifies Koopman operators from model parameter trajectories to adapt to evolving data distributions.
problem Adaptation of parametric models to non-stationary environments.
method Data-driven framework using Koopman operator identification and Extended Dynamic Mode Decomposition (EDMD).
result KOMET achieves high autonomous-rollout accuracies of 0.981 to 1.000 over 100 time steps on various drifting datasets.
Solves parameter non-identifiability in Bayesian LTI system identification.
problem Parameter non-identifiability in standard Bayesian approaches for LTI system identification.
method Embedding canonical forms of LTI systems within the Bayesian framework.
result Unlocking the use of meaningful priors and robust uncertainty estimates.
New method identifies physical constants from video data alone.
problem Identifying physical constants from video data.
method Proves level-set slope-coverage condition ensures local affine mapping to true physical state, enabling exact parameter recovery.
result Underdamped systems identifiable from a single video clip, other regimes require three diverse trajectories.
Hierarchical Latent Attribute Models (HLAMs) are a family of discrete latent variable models that are attracting increasing attention in educational, psychological, and behavioral sciences. The key ingredients of an HLAM include a binary structural matrix and a directed acyclic graph specifying hierarchical constraints…
Improved learning of probabilistic box embeddings by modeling parameters with Gumbel distributions.
problem Local identifiability issues in geometric embeddings.
method Modeling box parameters with min and max Gumbel distributions, calculating expected intersection volume.
result Improves the ability of probabilistic box embeddings to learn.
SSRCA simplifies ABM sensitivity analysis using machine learning.
problem Hardness of performing sensitivity analysis for complex ABMs.
method Machine learning pipeline (Simulate, Summarize, Reduce, Cluster, Analyze) for ABMs.
result SSRCA identifies sensitive parameters and common output patterns for ABMs.
This work studies the parameter identification problem for the Markov chain choice model of Blanchet, Gallego, and Goyal used in assortment planning. In this model, the product selected by a customer is determined by a Markov chain over the products, where the products in the offered assortment are absorbing states. Th…
This paper studies identifiability and convergence behaviors for parameters of multiple types in finite mixtures, and the effects of model fitting with extra mixing components. First, we present a general theory for strong identifiability, which extends from the previous work of Nguyen [2013] and Chen [1995] to address…
Study on the limits of learning HMM parameters under various conditions.
problem Understanding the conditions under which hidden Markov model parameters can be learned.
method Nonasymptotic minimax upper and lower bounds, thresholds analysis.
result Nonasymptotic minimax bounds match up to constants, showing learnable thresholds.
Atlas models are systems of Ito processes with parameters that depend on rank. We show that the parameters of a simple Atlas model can be identified by measuring the variance of the top-ranked process for different sampling intervals.
Unified framework certifies predictor performance under distribution shift.
problem Certifying predictor performance under distribution shift.
method Unified framework with explicit inequalities, sound verification, and identifiable structure.
result Explicit upper bound on excess risk under shift.
Study identifies key parameters and input dimensions making LLMs and VLMs brittle.
problem Vulnerability of large language and vision-language models to perturbations.
method Proposed FI measure based on information geometry to quantify sensitivity.
result Small subset of high FI parameters significantly contribute to brittleness.
Framework synthesizes programs for simulating complex models and estimating parameters.
problem Parameter estimation for complex models requires manual encoding of fixed model structures.
method Combines LLMs for program synthesis with neural simulation-based inference.
result Identifies plausible model families from open-ended prompts with high accuracy.
Solves challenges in estimating parameters of softmax gating Gaussian mixture models.
problem Identifiability issues and complex interactions in Gaussian mixture of experts.
method Proposes novel Voronoi loss functions and establishes convergence rates of MLE.
result Connects convergence rate of MLE to a solvability problem of polynomial equations.
With the advent of modern data collection and storage technologies, data-driven approaches have been developed for discovering the governing partial differential equations (PDE) of physical problems. However, in the extant works the model parameters in the equations are either assumed to be known or have a linear depen…
Quantum oracles help identify counterfactuals better than classical ones.
problem Identifying unknown causal parameters in causal models.
method Using quantum oracles to query and identify all causal parameters and counterfactuals.
result Quantum oracles enable identification of all two-way joint counterfactuals and tighter bounds on higher-order counterfactuals.
We orthogonalize the NSS model to condition and diagnose its ill-conditioned parameters.
problem The ill-conditioning of the NSS model's design matrix.
method Exact orthogonal reparametrization via QR decomposition.
result Orthogonalization isolates the conditioning structure and maintains fit uncertainty.
We employ unsupervised machine learning techniques to learn latent parameters which best describe states of the two-dimensional Ising model and the three-dimensional XY model. These methods range from principal component analysis to artificial neural network based variational autoencoders. The states are sampled using …
New neural network approach for optimizing latent variable models.
problem Stability issues in marginalizing Gaussian Bayesian networks.
method Developed a new graphical structure and a neural network algorithm.
result Established a duality between parameter optimization and neural network training.
Computational identifiability is a new framework for identifying causal effects.
problem Identifying causal effects in complex scenarios.
method A computational search procedure for empirical estimators.
result Fine-grained identification questions can be answered.
Study identifies parameters in causal models with latent confounding.
problem Parameter identification in linear non-Gaussian causal models with latent confounding.
method Graphical criterion for necessary and sufficient identifiability of direct causal effects, with polynomial-time algorithm.
result Developed a graphical criterion for identifying direct causal effects in latent variable models with arbitrary non-linear confounding.
Neural point estimators improve parameter estimation from replicated data.
problem Making inference from replicated data in weakly-identified and highly-parameterised models.
method Permutation-invariant neural networks for likelihood-free parameter estimation.
result Neural point estimators can quickly and optimally estimate parameters.
The degree-d Chow parameters of a Boolean function f:{−1,1}n→R are its degree at most d Fourier coefficients. It is well-known that degree-d Chow parameters uniquely characterize degree-d polynomial threshold functions (PTFs) within the space of all bounded functions. In this paper, we prove …
Paper addresses identifiability and asymptotics of ODE systems from noisy data.
problem Identifying parameters and causal structure of linear ODE systems from discrete observations.
method Developed sufficient conditions for identifiability, proved consistency and asymptotic normality of NLS estimator, constructed confidence sets, and inferred causal structure.
result Consistent and asymptotically normal parameter estimator for linear ODE systems under mild conditions.
New phases identified in neural scaling laws with compute limits.
problem Understanding neural scaling laws under compute constraints.
method Solved neural scaling model with stochastic gradient descent, derived loss curves, analyzed model-parameter-count phases.
result Identified 4 phases (+3 subphases) in data-complexity/target-complexity phase-plane, derived exponents.
The paper uses AI to analyze on-chain parameters and identify risky cryptocurrencies.
problem Identifying risky cryptocurrencies and understanding their price factors.
method Historical data analysis, AI algorithms, clustering, classification.
result A significant negative correlation between cryptocurrency price and maximum and total supply, and a weak positive correlation with 24-hour trading volume.
In the biclustering problem, we seek to simultaneously group observations and features. While biclustering has applications in a wide array of domains, ranging from text mining to collaborative filtering, the problem of identifying structure in high dimensional genomic data motivates this work. In this context, biclust…
This paper explores unsupervised learning of parsing models along two directions. First, which models are identifiable from infinite data? We use a general technique for numerically checking identifiability based on the rank of a Jacobian matrix, and apply it to several standard constituency and dependency parsing mode…
New method identifies structural parameters without assuming uncorrelated errors.
problem Identifying structural parameters in simultaneous equation models.
method Exploits higher-order cumulant restrictions, not requiring uncorrelated errors.
result Simple diagonality condition on hth-order cumulants identifies structural parameter matrix. SBI helps scientists match model outputs to data.
problem Tuning simulator parameters to match empirical data is hard.
method Simulation-based inference (SBI) identifies compatible parameter sets.
result SBI quantifies parameter uncertainty by identifying high-probability regions.