mlsanityData to 7 Oct 2026

Computationally efficient reductions between some statistical models

arXiv 2402.07717 ↗First posted 12 Feb 2024math.ST cs.IT math.ITcited by 0

Not on the map. Why?

Abstract (arXiv)

We study the problem of approximately transforming a sample from a source statistical model to a sample from a target statistical model without knowing the parameters of the source model, and construct several computationally efficient such reductions between canonical statistical experiments. In particular, we provide computationally efficient procedures that approximately reduce uniform, Erlang, and Laplace location models to general target families. We illustrate our methodology by establishing nonasymptotic reductions between some canonical high-dimensional problems, spanning mixtures of experts, phase retrieval, and signal denoising. Notably, the reductions are structure-preserving and can accommodate missing data. We also point to a possible application in transforming one differentially private mechanism to another.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 29 of its 108 references that are in the map. First posted on arXiv 12 Feb 2024.

Builds on

29 of 108 references.

References · 29

  1. 2014Statistical guarantees for the EM algorithm: From population to sample-based analysiscited by 131
  2. 2014Phase Retrieval via Wirtinger Flow: Theory and Algorithmscited by 123
  3. 2019Notes on Computational Hardness of Hypothesis Testing: Predictions using the Low-Degree Likelihood Ratiocited by 82
  4. 2020Reducibility and Statistical-Computational Gaps from Secret Leakagecited by 50
  5. 2018Reducibility and Computational Lower Bounds for Problems with Planted Sparse Structurecited by 35
  6. 2020Tensor Clustering with Planted Structures: Statistical Optimality and Computational Limitscited by 29
  7. 2016PhaseMax: Convex Phase Retrieval via Basis Pursuitcited by 25
  8. 2017Solving (most) of a set of quadratic equalities: Composite optimization for robust phase retrievalcited by 24
  9. 2015Optimal Rates of Convergence for Noisy Sparse Phase Retrieval via Thresholded Wirtinger Flowcited by 23
  10. 2020Exact Clustering in Tensor Block Model: Statistical Optimality and Computational Limitcited by 23
  11. 2014Computational Lower Bounds for Community Detection on Random Graphscited by 21
  12. 2017Phase Retrieval via Randomized Kaczmarz: Theoretical Guaranteescited by 15
17 more
  1. 2018Breaking the gridlock in Mixture-of-Experts: Consistent and Efficient Algorithmscited by 13
  2. 2019Universality of Computational Lower Bounds for Submatrix Detectioncited by 13
  3. 2019Optimal Average-Case Reductions to Sparse PCA: From Weak Assumptions to Strong Hardnesscited by 13
  4. 2020Isotonic regression with unknown permutations: Statistics, computation, and adaptationcited by 13
  5. 2022Alternating minimization for generalized rank one matrix sensing: Sharp predictions from a random initializationcited by 9
  6. 2018The Generalized Lasso for Sub-gaussian Measurements with Dithered Quantizationcited by 8
  7. 2020Hypothesis testing with low-degree polynomials in the Morris class of exponential familiescited by 7
  8. 2023Statistical-Computational Tradeoffs in Mixed Sparse Linear Regressioncited by 7
  9. 2019Low-rank matrix completion and denoising under Poisson noisecited by 6
  10. 2020Algebraic and Analytic Approaches for Parameter Learning in Mixture Modelscited by 4
  11. 2024Hyperparameter tuning via trajectory predictions: Stochastic prox-linear methods in matrix sensingcited by 4
  12. 2018Breaking the 1/√n Barrier: Faster Rates for Permutation-based Models in Polynomial Timecited by 3
  13. 2022A Dual Accelerated Method for Online Stochastic Distributed Averaging: From Consensus to Decentralized Policy Evaluationcited by 3
  14. 2014Noisy Matrix Completion under Sparse Factor Modelscited by 2
  15. 2015Minimax Lower Bounds for Noisy Matrix Completion Under Sparse Factor Modelscited by 1
  16. 2022A Cross Validation Framework for Signal Denoising with Applications to Trend Filtering, Dyadic CART and Beyondcited by 1
  17. 2023Do algorithms and barriers for sparse principal component analysis extend to other structured settings?cited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Data denoising with self consistency, variance maximization, and the Kantorovich dominance
  2. 2025When Models Don't Collapse: On the Consistency of Iterative MLE
  3. 2023Adapt and Diffuse: Sample-adaptive Reconstruction via Latent Diffusion Models
  4. 2025Normalization-equivariant Diffusion Models: Learning Posterior Samplers From Noisy And Partial Measurements
  5. 2026Unlearning in Diffusion Models: A Unified Framework with KL Divergence and Likelihood Constraints
  6. 2024DEFT: Efficient Fine-Tuning of Diffusion Models by Learning the Generalised h-transform
  7. 2026Continual Data Unlearning in Diffusion Models via Transition-based Regularization
  8. 2026Leveraging Inference-Time Compute for Diffusion Models via Global Scheduling of Denoising Trajectories