2024
Wyner-Ziv Estimators for Distributed Mean Estimation With Side Information and Optimization.
IEEE Trans. Inf. Theory, April, 2024
Multi-Group Fairness Evaluation via Conditional Value-at-Risk Testing.
IEEE J. Sel. Areas Inf. Theory, 2024
InfAlign: Inference-aware language model alignment.
,
,
,
,
,
,
,
,
,
,
,
CoRR, 2024
Rate of Model Collapse in Recursive Training.
CoRR, 2024
Coupling without Communication and Drafter-Invariant Speculative Decoding.
CoRR, 2024
Private federated discovery of out-of-vocabulary words for Gboard.
CoRR, 2024
Towards Fast Inference: Exploring and Improving Blockwise Parallel Drafts.
CoRR, 2024
Optimal Block-Level Draft Verification for Accelerating Speculative Decoding.
CoRR, 2024
Efficient Language Model Architectures for Differentially Private Federated Learning.
CoRR, 2024
Theoretical guarantees on the best-of-n alignment policy.
CoRR, 2024
Accelerating Blockwise Parallel Language Models with Draft Refinement.
Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 2024
Asymptotics of Language Model Alignment.
Proceedings of the IEEE International Symposium on Information Theory, 2024
Mean Estimation in the Add-Remove Model of Differential Privacy.
Proceedings of the Forty-first International Conference on Machine Learning, 2024
The importance of feature preprocessing for differentially private linear optimization.
Proceedings of the Twelfth International Conference on Learning Representations, 2024
FedAQT: Accurate Quantized Training with Federated Learning.
Proceedings of the IEEE International Conference on Acoustics, 2024
2023
FedYolo: Augmenting Federated Learning with Pretrained Transformers.
CoRR, 2023
SpecTr: Fast Speculative Decoding via Optimal Transport.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023
Concentration Bounds for Discrete Distribution Estimation in KL Divergence.
Proceedings of the IEEE International Symposium on Information Theory, 2023
Algorithms for bounding contribution for histogram estimation under user-level privacy.
Proceedings of the International Conference on Machine Learning, 2023
Federated Heavy Hitter Recovery under Linear Sketching.
Proceedings of the International Conference on Machine Learning, 2023
Subset-Based Instance Optimality in Private Estimation.
Proceedings of the International Conference on Machine Learning, 2023
Principled Approaches for Private Adaptation from a Public Source.
Proceedings of the International Conference on Artificial Intelligence and Statistics, 2023
2022
Private Domain Adaptation from a Public Source.
CoRR, 2022
Histogram Estimation under User-level Privacy with Heterogeneous Data.
CoRR, 2022
Scaling Language Model Size in Cross-Device Federated Learning.
CoRR, 2022
Differentially Private Learning with Margin Guarantees.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022
Correlated Quantization for Distributed Mean Estimation and Optimization.
Proceedings of the International Conference on Machine Learning, 2022
The Fundamental Price of Secure Aggregation in Differentially Private Federated Learning.
Proceedings of the International Conference on Machine Learning, 2022
On the benefits of maximum likelihood estimation for Regression and Forecasting.
Proceedings of the Tenth International Conference on Learning Representations, 2022
Robust Estimation for Random Graphs.
Proceedings of the Conference on Learning Theory, 2-5 July 2022, London, UK., 2022
2021
Shuffled Model of Federated Learning: Privacy, Accuracy and Communication Trade-Offs.
IEEE J. Sel. Areas Inf. Theory, 2021
Advances and Open Problems in Federated Learning.
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
Found. Trends Mach. Learn., 2021
HD-cos Networks: Efficient Neural Architectures for Secure Multi-Party Computation.
CoRR, 2021
FedJAX: Federated learning simulation with JAX.
CoRR, 2021
A Field Guide to Federated Optimization.
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
CoRR, 2021
Approximating Probabilistic Models as Weighted Finite Automata.
Comput. Linguistics, 2021
Remember What You Want to Forget: Algorithms for Machine Unlearning.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021
Learning with User-Level Privacy.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021
Breaking the centralized barrier for cross-device federated learning.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021
Boosting with Multiple Sources.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021
Communication-Efficient Agnostic Federated Averaging.
Proceedings of the 22nd Annual Conference of the International Speech Communication Association, Interspeech 2021, Brno, Czechia, August 30, 2021
A Discriminative Technique for Multiple-Source Adaptation.
Proceedings of the 38th International Conference on Machine Learning, 2021
Relative Deviation Margin Bounds.
Proceedings of the 38th International Conference on Machine Learning, 2021
On the Rényi Differential Privacy of the Shuffle Model.
Proceedings of the CCS '21: 2021 ACM SIGSAC Conference on Computer and Communications Security, Virtual Event, Republic of Korea, November 15, 2021
Robust hypothesis testing and distribution estimation in Hellinger distance.
Proceedings of the 24th International Conference on Artificial Intelligence and Statistics, 2021
Wyner-Ziv Estimators: Efficient Distributed Mean Estimation with Side-Information.
Proceedings of the 24th International Conference on Artificial Intelligence and Statistics, 2021
A Theory of Multiple-Source Adaptation with Limited Target Labeled Data.
Proceedings of the 24th International Conference on Artificial Intelligence and Statistics, 2021
Shuffled Model of Differential Privacy in Federated Learning.
Proceedings of the 24th International Conference on Artificial Intelligence and Statistics, 2021
2020
Multiple-Source Adaptation with Domain Classifiers.
CoRR, 2020
Shuffled Model of Federated Learning: Privacy, Communication and Accuracy Trade-offs.
CoRR, 2020
Mime: Mimicking Centralized Stochastic Algorithms in Federated Learning.
CoRR, 2020
A Theory of Multiple-Source Adaptation with Limited Target Labeled Data.
CoRR, 2020
Three Approaches for Personalization with Applications to Federated Learning.
CoRR, 2020
Learning discrete distributions: user vs item-level privacy.
Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020
SCAFFOLD: Stochastic Controlled Averaging for Federated Learning.
Proceedings of the 37th International Conference on Machine Learning, 2020
FedBoost: A Communication-Efficient Algorithm for Federated Learning.
Proceedings of the 37th International Conference on Machine Learning, 2020
Optimal multiclass overfitting by sequence reconstruction from Hamming queries.
Proceedings of the Algorithmic Learning Theory, 2020
2019
Advances and Open Problems in Federated Learning.
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
CoRR, 2019
Can You Really Backdoor Federated Learning?
CoRR, 2019
SCAFFOLD: Stochastic Controlled Averaging for On-Device Federated Learning.
CoRR, 2019
AdaCliP: Adaptive Clipping for Private SGD.
CoRR, 2019
Differentially Private Anonymized Histograms.
Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019
Sampled Softmax with Random Fourier Features.
Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019
Convergence of Chao Unseen Species Estimator.
Proceedings of the IEEE International Symposium on Information Theory, 2019
Agnostic Federated Learning.
Proceedings of the 36th International Conference on Machine Learning, 2019
West: Word Encoded Sequence Transducers.
Proceedings of the IEEE International Conference on Acoustics, 2019
Distilling weighted finite automata from arbitrary probabilistic models.
Proceedings of the 14th International Conference on Finite-State Methods and Natural Language Processing, 2019
Federated Learning of N-Gram Language Models.
Proceedings of the 23rd Conference on Computational Natural Language Learning, 2019
2018
Maximum Selection and Sorting with Adversarial Comparators.
J. Mach. Learn. Res., 2018
Data Amplification: A Unified and Competitive Approach to Property Estimation.
Proceedings of the Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, 2018
cpSGD: Communication-efficient and differentially-private distributed SGD.
Proceedings of the Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, 2018
2017
Estimating Renyi Entropy of Discrete Distributions.
IEEE Trans. Inf. Theory, 2017
Multiscale Quantization for Fast Similarity Search.
Proceedings of the Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, 2017
Model-Powered Conditional Independence Test.
Proceedings of the Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, 2017
Minimax risk for missing mass estimation.
Proceedings of the 2017 IEEE International Symposium on Information Theory, 2017
Distributed Mean Estimation with Limited Communication.
Proceedings of the 34th International Conference on Machine Learning, 2017
Maximum Selection and Ranking under Noisy Comparisons.
Proceedings of the 34th International Conference on Machine Learning, 2017
A Unified Maximum Likelihood Approach for Estimating Symmetric Properties of Discrete Distributions.
Proceedings of the 34th International Conference on Machine Learning, 2017
Sample complexity of population recovery.
Proceedings of the 30th Conference on Learning Theory, 2017
Lattice rescoring strategies for long short term memory language models in speech recognition.
Proceedings of the 2017 IEEE Automatic Speech Recognition and Understanding Workshop, 2017
2016
A Unified Maximum Likelihood Approach for Optimal Distribution Property Estimation.
Electron. Colloquium Comput. Complex., 2016
Federated Learning: Strategies for Improving Communication Efficiency.
CoRR, 2016
Maximum Selection and Sorting with Adversarial Comparators and an Application to Density Estimation.
CoRR, 2016
Orthogonal Random Features.
Proceedings of the Advances in Neural Information Processing Systems 29: Annual Conference on Neural Information Processing Systems 2016, 2016
Learning Markov distributions: Does estimation trump compression?
Proceedings of the IEEE International Symposium on Information Theory, 2016
Estimating the number of defectives with group testing.
Proceedings of the IEEE International Symposium on Information Theory, 2016
2015
Competitive Distribution Estimation.
CoRR, 2015
The Complexity of Estimating Rényi Entropy.
Proceedings of the Twenty-Sixth Annual ACM-SIAM Symposium on Discrete Algorithms, 2015
Competitive Distribution Estimation: Why is Good-Turing Good.
Proceedings of the Advances in Neural Information Processing Systems 28: Annual Conference on Neural Information Processing Systems 2015, 2015
Automata and graph compression.
Proceedings of the IEEE International Symposium on Information Theory, 2015
Universal compression of power-law distributions.
Proceedings of the IEEE International Symposium on Information Theory, 2015
On Learning Distributions from their Samples.
Proceedings of The 28th Conference on Learning Theory, 2015
Faster Algorithms for Testing under Conditional Sampling.
Proceedings of The 28th Conference on Learning Theory, 2015
Sparse Solutions to Nonnegative Linear Systems and Applications.
Proceedings of the Eighteenth International Conference on Artificial Intelligence and Statistics, 2015
2014
Universal Compression of Envelope Classes: Tight Characterization via Poisson Sampling.
CoRR, 2014
Near-Optimal-Sample Estimators for Spherical Gaussian Mixtures.
Proceedings of the Advances in Neural Information Processing Systems 27: Annual Conference on Neural Information Processing Systems 2014, 2014
Sublinear algorithms for outlier detection and generalized closeness testing.
Proceedings of the 2014 IEEE International Symposium on Information Theory, Honolulu, HI, USA, June 29, 2014
Poissonization and universal compression of envelope classes.
Proceedings of the 2014 IEEE International Symposium on Information Theory, Honolulu, HI, USA, June 29, 2014
Efficient compression of monotone and m-modal distributions.
Proceedings of the 2014 IEEE International Symposium on Information Theory, Honolulu, HI, USA, June 29, 2014
Sorting with adversarial comparators and application to density estimation.
Proceedings of the 2014 IEEE International Symposium on Information Theory, Honolulu, HI, USA, June 29, 2014
2013
Interplay Between Optimal Selection Scheme, Selection Criterion, and Discrete Rate Adaptation in Opportunistic Wireless Systems.
IEEE Trans. Commun., 2013
Tight bounds for universal compression of large alphabets.
Proceedings of the 2013 IEEE International Symposium on Information Theory, 2013
Optimal Probability Estimation with Applications to Prediction and Classification.
Proceedings of the COLT 2013, 2013
A Competitive Test for Uniformity of Monotone Distributions.
Proceedings of the Sixteenth International Conference on Artificial Intelligence and Statistics, 2013
2012
Competitive Classification and Closeness Testing.
Proceedings of the COLT 2012, 2012
On the query computation and verification of functions.
Proceedings of the 2012 IEEE International Symposium on Information Theory, 2012
2010
Strong secrecy for erasure wiretap channels.
Proceedings of the 2010 IEEE Information Theory Workshop, 2010