For about a dozen years I had a grand time in academia working with some incredible people; see below for the work we did together. I was a postdoc with Emmanuel Candès at Stanford University after completing my Ph.D. under Richard G. Baraniuk in the DSP Group at Rice University. Ich war auch für ein Semester zur Gastpromotion bei Prof Reinhard Heckel an der Technische Universität München. Before that, I obtained my M.S. from University of Michigan (Go Blue!) and my B.S. from McNeese State University, all in electrical engineering.
Preprints
-
P. T. Nobel, D. LeJeune, E. J. Candès.
“RandALO: Out-of-sample risk estimation in no time flat,” 2024, Submitted to JMLR.
2025
-
M. Dereziński, D. LeJeune, D. Needell, E. Rebrova.
“Fine-grained analysis and faster algorithms for iteratively solving linear systems,” 2025, Accepted to JMLR.
2024
-
Y. Dar, D. LeJeune, R. G. Baraniuk.
“The common intuition to transfer learning can win or lose: Case studies for linear regression,” 2024, SIMODS.
SIMODS
-
D. LeJeune, J. Liu, R. Heckel.
“Monotonic risk relationships under distribution shifts for regularized risk minimization,” 2024, JMLR.
JMLR
-
P. Patil, D. LeJeune.
“Asymptotically free sketched ridge ensembles: Risks, cross-validation, and tuning,” 2024, ICLR.
OpenReview
-
S. Alemohammad, J. Casco-Rodriguez, L. Luzi, A. I. Humayun, H. Babaei, D. LeJeune, A. Siahkoohi, R. G. Baraniuk.
“Self-consuming generative models go MAD,” 2023, ICLR.
OpenReview
-
D. LeJeune, P. Patil, H. Javadi, R. G. Baraniuk, R. J. Tibshirani.
“Asymptotics of the sketched pseudoinverse,” 2024, SIMODS.
SIMODS
-
D. LeJeune, S. Alemohammad.
“An adaptive tangent feature perspective of neural networks,” 2024, CPAL.
OpenReview
-
L. Luzi, D. LeJeune, A. Siahkoohi, S. Alemohammad, V. Saragadam, H. Babaei, N. Liu, Z. Wang, R. G. Baraniuk.
“TITAN: Bringing the deep image prior to implicit representations,” 2024, ICASSP.
IEEE Xplore
2023
-
P. K. Kota, H. Vu, D. LeJeune, M. Han, S. Syed, R. G. Baraniuk, R. A. Drezek.
“Expanded multiplexing on sensor-constrained microfluidic partitioning systems,” 2023, Analytical Chemistry.
ACS
-
V. Saragadam, D. LeJeune, J. Tan, G. Balakrishnan, A. Veeraraghavan, R. G. Baraniuk.
“WIRE: Wavelet implicit neural representations,” 2023, CVPR.
Website
CVF
-
J. Tan, D. LeJeune, B. Mason, H. Javadi, R. G. Baraniuk.
“A blessing of dimensionality in membership inference through regularization,” 2023, AISTATS.
PMLR
2022
-
D. LeJeune.
“Ridge regularization by randomization in linear ensembles,” 2022, Ph.D. thesis.
Rice Research Repository
-
D. LeJeune, J. Liu, R. Heckel.
“Monotonic risk relationships under distribution shifts for regularized risk minimization,” 2022, ICML PODS Workshop.
-
P. K. Kota, D. LeJeune, R. A. Drezek, R. G. Baraniuk.
“Extreme compressed sensing of Poisson rates from multiple measurements,” 2022, IEEE Transactions on Signal Processing.
IEEE Xplore
2021
-
D. LeJeune, H. Javadi, R. G. Baraniuk.
“The flip side of the reweighted coin: Duality of adaptive dropout and regularization,” 2021, NeurIPS.
NeurIPS
-
S. Alemohammad, H. Babaei, R. Balestriero, M. Y. Cheung, A. I. Humayun, D. LeJeune, N. Liu, L. Luzi, J. Tan, R. G. Baraniuk.
“Wearing a MASK: Compressed representations of variable-length sequences using recurrent neural tangent kernels,” 2021, ICASSP.
IEEE Xplore
-
T. Yao, D. LeJeune, H. Javadi, R. G. Baraniuk, G. I. Allen.
“Minipatch learning as implicit ridge-like regularization,” 2021, IEEE BigComp.
IEEE Xplore
2020
-
D. LeJeune, H. Javadi, R. G. Baraniuk.
“The implicit regularization of ordinary least squares ensembles,” 2020, AISTATS.
PMLR
-
D. LeJeune, G. Dasarathy, R. G. Baraniuk.
“Thresholding graph bandits with GrAPL,” 2020, AISTATS.
PMLR
2019
-
D. LeJeune, R. Heckel, R. G. Baraniuk.
“Adaptive estimation for approximate k-nearest-neighbor computations,” 2019, AISTATS.
PMLR
-
D. LeJeune, R. Balestriero, H. Javadi, R. G. Baraniuk.
“Implicit rugosity regularization via data augmentation,” 2019.