2026

“Exploratory Causal Inference in SAEnce”
T. Mencattini*, R. Cadei*, F. Locatello
ICLR, 2026.

“High-dimensional Analysis of Synthetic Data Selection”
P. Rezaei, F. Kovacevic, F. Locatello*, M. Mondelli*
ICLR, 2026.

“Learning explicit single-cell dynamics using ODE representations”
J.P. von Bassewitz, A. Pervez, M. Fumero, M. Robinson, T. Karaletsos, F. Locatello
ICLR, 2026.

“Boomerang Distillation Enables Zero-Shot Model Size Interpolation”
S. Kangaslahti, N. V. Nayak, J. Geuter, M. Fumero, F. Locatello, D. Alvarez-Melis
ICLR, 2026.

“Navigating the Latent Space Dynamics of Neural Models“
M. Fumero, L. Moschella, E. Rodolà*, F. Locatello*
ICLR, 2026.

“Statistical and Structural Identifiability in Self-Supervised Learning”
W. Nelson, M. Fumero, T. Karaletsos, F. Locatello
ICLR, 2026.

“On the identifiability of causal graphs with multiple environments”
F. Montagna
ICLR, 2026.

“A Law of Data Reconstruction for Random Features (and Beyond)“
L. Iurada*, S. Bombari*, T. Tommasi, M. Mondelli*
ICLR, 2026.

“The Geometry of LLM Quantization: GPTQ as Babai’s Nearest Plane Algorithm”
J. Chen, Y. Shabanzadeh, E. Crnčević, T. Hoefler, D. Alistarh
ICLR, 2026.

“The Unseen Frontier: Pushing the Limits of LLM Sparsity with Surrogate-Free ADMM”
K. Lee, H. Jang, D. Lee, D. Alistarh, N. Lee
ICLR, 2026.

“Bridging the Gap Between Promise and Performance for FP4 Quantization”
V. Egiazarian, R. L. Castro, D. Kuznedelev, A. Panferov, S. Ashkboos, E. Kurtic, S. Pandit, A. N. Marques, M. Kurtz, T. Hoefler, D. Alistarh
ICLR, 2026.

“Beyond Outliers: A Study of Optimizers Under Quantization”
G. Vlassis, S. Ashkboos, A. Volkova, T. Hoefler, D. Alistarh
ICLR, 2026.

“FFT-Based Dynamic Subspace Selection for Low-Rank Adaptive Optimization of Large Language Models”
I. Modoranu, M. Safaryan, E. Schultheis, M. Ryabinin, A. Chumachenko, D. Alistarh
ICLR, 2026.

“Back to Square Roots: An Optimal Bound on the Matrix Factorization Error for Multi-Epoch Differentially Private SGD”
N. Kalinin, J. Upadhyay, R. McKenna, C. H. Lampert
ICLR, 2026.

“ASIDE: Architectural Separation of Instructions and Data in Language Models”
E. Zverev, E. Kortukov, A. Panfilov, A. Volkova, R. Tabesh, S. Lapuschkin, W. Samek, C. H. Lampert
ICLR, 2026.

“Representing local protein environments with machine learning force fields”
M. Bojan, S. Vedula, A. Maddipatla, N. B. Sellam, F. Napoli, P. Standee, A. M. Bronstein
ICLR, 2026.

2025

“Can LLMs Separate Instructions From Data? And What Do We Even Mean By That?”
E. Zverev, S. Abdelnabi, S. Tabesh, M. Fritz, Christoph H. Lampert
ICLR, 2025

“How to Probe: Simple Yet Effective Techniques for Improving Post-hoc Explanations”
S. Gairola, M. Böhle, F. Locatello, B. Schiele
ICLR, 2025

“Mechanistic PDE Networks for Discovery of Governing Equations”
A. Pervez, E. Gavves, F. Locatello
ICML, 2025

“Prediction-Powered Causal Inference”
R. Cadei, I. Demirel, P. De Bartolomeis, L. Lindorfer, S. Cremer, C. Schmid, F. Locatello
NeurIPS, 2025

“Connecting neural models latent geometries with relative geodesic representations”
H. Yu, B. Inal, G. Arvanitidis, S. Hauberg, F. Locatello, M. Fumero
NeurIPS, 2025

“Differentially Private Federated k-Means Clustering with Server-Side Data”
J. Scott, C. H. Lampert, D. Saulpic
ICML, 2025

“Logic Gate Neural Networks are Good for Verification”
F. Kresse, E. Yu, C. H. Lampert, T. A. Henzinger
NeuS, 2025

“Generalization in Multi-Objective Machine Learning”
P. Súkeník, C. H. Lampert
Neural Computing & Applications, 2025

“Differentially Private Continual Release of Histograms and Related Queries”
M. Henzinger, A. R. Sricharan, T. A. Steiner
Proceedings of The 28th International Conference on Artificial Intelligence and Statistics, 2025

“Near-Optimal Differentially Private Graph Algorithms via the Multidimensional Above Threshold Mechanism”
L. Dhulipala, M. Henzinger, G. Z. Li, Q. C. Liu, A. R. Sricharan, L. Zhu
ESA 2025

“Improved Differentially Private Continual Observation Using Group Algebra”
M. Henzinger, J. Upadhyay
SODA 2025

2024

“Privacy for Free in the Over-Parameterized Regime“
S. Bombari, M. Mondelli
arXiv, 2024

2023

2022

“Estimation in Rotationally Invariant Generalized Linear Models via Approximate Message Passing“
R. Venkataramanan, K. Kögler, and M. Mondelli
ICML, 2022

“Polar Coded Computing: The Role of the Scaling Exponent“
D. Fathollahi, M. Mondelli
ISIT, 2022

“Fairness-Aware PAC Learning from Corrupted Data”
N. Konstantinov, C. H. Lampert
JMLR, 2022

“Almost-Orthogonal Layers for Efficient General-Purpose Lipschitz Networks”
B. Prach, C. H. Lampert
ECCV, 2022

“Mean-ﬁeld Analysis of Piecewise Linear Solutions for Wide ReLU Networks“
A. Shevchenko, V. Kungurtsev, M. Mondelli
JMLR, 2022

“XX“
xx
xx

2021

“Approximate Message Passing with Spectral Initialization for Generalized Linear Models“
M. Mondelli, R. Venkataramanan
AISTATS, 2021

2020


GLOBAL CONVERGENCE OF DEEP NETWORKS WITH ONE WIDE LAYER FOLLOWED BY PYRAMIDAL TOPOLOGY NeurIPS 2020 Nguyen, Mondelli Paper	WOODFISHER: EFFICIENT SECOND-ORDER APPROXIMATION FOR NEURAL NETWORK COMPRESSION NeurIPS 2020 Singh, Alistarh Project Paper	RELAXED SCHEDULING FOR SCALABLE BELIEF PROPAGATION NeurIPS 2020 Aksenov, Alistarh Project Paper	UNSUPERVISED OBJECT-CENTRIC VIDEO GENERATION AND DECOMPOSITION IN 3D NeurIPS 2020 Henderson, Lampert Project Paper
COMPUTATIONAL DESIGN OF COLD BENT GLASS FAÇADES ACM Transactions on Graphics 39(6) (SIGGRAPH Asia 2020) Gavriil, Guseinov, Pérez, Pellis Henderson, Rist, Pottmann, Bickel Paper	BINARY LINEAR CODES WITH OPTIMAL SCALING: POLAR CODES WITH LARGE KERNELS IEEE Transactions on Information Theory Fazeli, Hassani, Mondelli, Vardy Paper	DOES SGD IMPLICITLY OPTIMIZE FOR SMOOTHNESS? GCPR 2020 Volhejn, Lampert Paper	LANDSCAPE CONNECTIVITY AND DROPOUT STABILITY OF SGD SOLUTIONS FOR OVER-PARAMETERIZED NEURAL NETWORKS ICML 2020 Shevchenko, Mondelli Paper
ON THE SAMPLE COMPLEXITY OF ADVERSARIAL MULTI-SOURCE PAC LEARNING ICML 2020 Konstantinov, Frantar, Alistarh, Lampert Paper	PROBABILISTIC INFERENCE OF THE GENETIC ARCHITECTURE OF FUNCTIONAL ENRICHMENT OF COMPLEX TRAITS medRxiv Patxot, Robinson Project Paper	BAYESIAN REASSESSMENT OF THE EPIGENETIC ARCHITECTURE OF COMPLEX TRAITS Nature Communications Trejo Banos, Robinson Paper	FUNCTIONAL VS. PARAMETRIC EQUIVALENCE OF RELU NETWORKS ICLR 2020 Phuong, Lampert Paper
LOCALIZING GROUPED INSTANCES FOR EFFICIENT DETECTION IN LOW-RESOURCE SCENARIOS WACV 2020 Royer, Lampert Project Paper	ANALYSIS OF A TWO-LAYER NEURAL NETWORK VIA DISPLACEMENT CONVEXITY Annals of Statistics Javanmard, Mondelli, Montanari Paper	A FLEXIBLE SELECTION SCHEME FOR MINIMUM-EFFORT TRANSFER LEARNING WACV 2020 Royer, Lampert Project Paper

2019

“Rate-flexible fast polar decoders”
S. A. Hashemi, C. Condo, M. Mondelli, W. J. Gross
IEEE Transactions on Signal Processing

“Distillation-Based Training for Multi-Exit Architectures”
M. Phuong, C. H. Lampert
ICCV, 2019

“Towards Understanding Knowledge Distillation”
M. Phuong, C. H. Lampert
ICML, 2019

“On the Connection Between Learning Two-Layer Neural Networks and Tensor Decomposition“
M. Mondelli, A. Montanari
AISTATS, 2019

“XX“
xx
xx

My Publication List

AC/DC: ALTERNATING COMPRESSED/DECOMPRESSED TRAINING OF DEEP NEURAL NETWORKS NeurIPS 2021 Peste, Iofinova, Vladu, Alistarh	DISTRIBUTED PRINCIPAL COMPONENT ANALYSIS WITH LIMITED COMMUNICATION NeurIPS 2021 Alimisis, Davies, Vandereycken, Alistarh	WHEN ARE SOLUTIONS CONNECTED IN DEEP NETWORKS? NeurIPS 2021 Nguyen Bréchet Mondelli	M-FAC: EFFICIENT MATRIX-FREE APPROXIMATIONS OF SECOND-ORDER INFORMATION NeurIPS 2021 Frantar Kurtic Alistarh
Project Paper	Project Paper		Project Paper
The Inductive Bias of RELU networks on orthogonally separable Data ICLR 2021 Phuong, Lampert	BYZANTINE-RESILIENT NON-CONVEX STOCHASTIC GRADIENT DESCENT ICLR 2021 Allen-Zhu, Ebrahimian, Li, Alistarh	TOWARDS TIGHT COMMUNICATION LOWER BOUNDS FOR DISTRIBUTED OPTIMIZATION NeurIPS 2021 Korhonen Alistarh	FULLY-ASYNCHRONOUS DECENTRALIZED SGD WITH QUANTIZED AND LOCAL UPDATES NeurIPS 2021 Nadiradze, Sabour, Davies, Li, Alistarh
Project Paper	Project Paper	Project Paper	Project Paper

PCA INITIALIZATION FOR APPROXIMATE MESSAGE PASSING IN ROTATIONALLY INVARIANT MODELS NeurIPS 2021 Mondelli, Venkataramanan	APPROXIMATE MESSAGE PASSING WITH SPECTRAL INITIALIZATION FOR GENERALIZED LINEAR MODELS AISTATS 2021 Mondelli, Venkataramanan	TIGHT BOUNDS ON THE SMALLEST EIGENVALUE OF THE NEURAL TANGENT KERNEL FOR DEEP RELU NETWORKS ICML 2021 Nguyen, Mondelli, Montufar	ONE-SIDED FRANK-WOLFE ALGORITHMS FOR SADDLE PROBLEMS ICML 2021 Kolmogorov, Pock
Paper	Paper	Paper	Paper
COMMUNICATION-EFFICIENT DISTRIBUTED OPTIMIZATION WITH QUANTIZED PRECONDITIONERS ICML 2021 Alimisis, Davies, Alistarh	GENOMIC ARCHITECTURE AND PREDICTION OF CENSORED TIME-TO-EVENT PHENOTYPES WITH A BAYESIAN GENOME-WIDE ANALYSIS Nature Communications Ojavee, Robinson	PARALLELISM VERSUS LATENCY IN SIMPLIFIED SUCCESSIVE-CANCELLATION DECODING OF POLAR CODES ISIT 2021 Hashemi, Mondelli, Fazeli, Vardy, Cioffi, Goldsmith	SPARSE MULTI-DECODER RECURSIVE PROJECTION AGGREGATION FOR REED-MULLER CODES ISIT 2021 Fathollahi, Farsad, Hashemi, Mondelli
Project Paper	Project Paper	Paper	Paper
NEW BOUNDS FOR DISTRIBUTED MEAN ESTIMATION AND VARIANCE REDUCTION ICLR 2021 Davies, Gurunanthan, Moshrefi, Ashkboos, Alistarh Project Paper OPTIMAL COMBINATION OF LINEAR AND SPECTRAL ESTIMATORS FOR GENERALIZED LINEAR MODELS Foundations of Computational Mathematics Mondelli, Thrampoulidis Venkataramanan Paper	ELASTIC CONSISTENCY: A PRACTICAL CONSISTENCY MODEL FOR DISTRIBUTED STOCHASTIC GRADIENT DESCENT AAAI 2021 Nadiradze, Markov, Chatterjee, Kungurtsev, Alistarh Project Paper	SPARSITY IN DEEP LEARNING: PRUNING AND GROWTH FOR EFFICIENT INFERENCE AND TRAINING IN NEURAL NETWORKS JMLR Hoefler, Alistarh, Ben-Nun, Dryden, Peste Project Paper	SUBLINEAR LATENCY FOR SIMPLIFIED SUCCESSIVE CANCELLATION DECODING OF POLAR CODES IEEE Transactions on Wireless Communications Mondelli, Hashemi, Cioffi, Goldsmith Paper


RATE-FLEXIBLE FAST POLAR DECODERS IEEE Transactions on Signal Processing Hashemi, Condo, Mondelli, Gross Paper	DISTILLATION-BASED TRAINING FOR MULTI-EXIT ARCHITECTURES ICCV 2019 Phuong, Lampert Paper	KS(CONF): A LIGHT-WEIGHT TEST IF A MULTICLASS CLASSIFIER OPERATES OUTSIDE OF ITS SPECIFICATIONS IJCV Sun, Lampert Project Paper	FUNCTION NORMS FOR NEURAL NETWORKS Workshop on Statistical Deep Learning in Computer Vision at ICCV 2019 Triki, Berman, Kolmogorov, Blaschko Paper
TESTING THE COMPLEXITY OF A VALUED CSP LANGUAGE ICALP 2019 Kolmogorov Project Paper	TOWARDS UNDERSTANDING KNOWLEDGE DISTILLATION ICML 2019 Phuong, Lampert Paper	ROBUST LEARNING FROM UNTRUSTED SOURCES ICML 2019 Konstantinov, Lampert Project Paper	MAP INFERENCE VIA BLOCK-COORDINATE FRANK-WOLFE ALGORITHM CVPR 2019 Swoboda, Kolmogorov Project Paper
ON THE CONNECTION BETWEEN LEARNING TWO-LAYERS NEURAL NETWORKS AND TENSOR DECOMPOSITION AISTATS 2019 Mondelli, Montanari Paper