Search Results for author:
Found 27 papers, 19 papers with code
InfoGAN-CR: Disentangling Generative Adversarial Networks with Contrastive Regularizers
This contrastive regularizer is inspired by a natural notion of disentanglement: latent traversal.
Truncated Consistency Models
Consistency models have recently been introduced to accelerate sampling from diffusion models by directly predicting the solution (i. e., data) of the probability flow ODE (PF ODE) from initial noise.
Data Distribution Valuation
Data valuation is a class of techniques for quantitatively assessing the value of data for applications like pricing in data marketplaces.
PrE-Text: Training Language Models on Private Federated Data in the Age of LLMs
Altogether, these results suggest that training on DP synthetic data can be a better option than training a model on-device on private distributed data.
Improving the Training of Rectified Flows
In this work, we propose improved techniques for training rectified flows, allowing them to compete with \emph{knowledge distillation} methods even in the low NFE setting.
Ranked #17 on
Image Generation
on ImageNet 64x64
On the Convergence of Differentially-Private Fine-tuning: To Linearly Probe or to Fully Fine-tune?
We provide theoretical insights into the convergence of DP fine-tuning within an overparameterized neural network and establish a utility curve that determines the allocation of privacy budget between linear probing and full fine-tuning.
Mixture-of-Linear-Experts for Long-term Time Series Forecasting
By using MoLE existing linear-centric models can achieve SOTA LTSF results in 68% of the experiments that PatchTST reports and we compare to, whereas existing single-head linear-centric models achieve SOTA results in only 25% of cases.
Ranked #1 on
Time Series Forecasting
on Electricity (720)
Pretrained deep models outperform GBDTs in Learning-To-Rank under label scarcity
On tabular data, a significant body of literature has shown that current deep learning (DL) models perform at best similarly to Gradient Boosted Decision Trees (GBDTs), while significantly underperforming them on outlier data.
Summary Statistic Privacy in Data Sharing
We study a setting where a data holder wishes to share data with a receiver, without revealing certain summary statistics of the data distribution (e. g., mean, standard deviation).
Privately Customizing Prefinetuning to Better Match User Data in Federated Learning
To this end, we propose FreD (Federated Private Fr\'echet Distance) -- a privately computed distance between a prefinetuning dataset and federated datasets.
On the Privacy Properties of GAN-generated Samples
By drawing connections to the generalization properties of GANs, we prove that under some assumptions, GAN-generated samples inherently satisfy some (weak) privacy guarantees.
Towards a Defense Against Federated Backdoor Attacks Under Continuous Training
We propose shadow learning, a framework for defending against backdoor attacks in the FL setting under long-range training.
RareGAN: Generating Samples for Rare Classes
We study the problem of learning generative adversarial networks (GANs) for a rare class of an unlabeled dataset subject to a labeling budget.
FedChain: Chained Algorithms for Near-Optimal Communication Cost in Federated Learning
We propose FedChain, an algorithmic framework that combines the strengths of local methods and global methods to achieve fast convergence in terms of R while leveraging the similarity between clients.
Abusive Language Detection in Heterogeneous Contexts: Dataset Collection and the Role of Supervised Attention
Abusive language is a massive problem in online social platforms.
Self-Supervised Euphemism Detection and Identification for Content Moderation
It is usually apparent to a human moderator that a word is being used euphemistically, but they may not know what the secret meaning is, and therefore whether the message violates policy.
Efficient Algorithms for Federated Saddle Point Optimization
Our goal is to design an algorithm that can harness the benefit of similarity in the clients while recovering the Minibatch Mirror-prox performance under arbitrary heterogeneity (up to log factors).
Why Spectral Normalization Stabilizes GANs: Analysis and Improvements
Spectral normalization (SN) is a widely-used technique for improving the stability and sample quality of Generative Adversarial Networks (GANs).
SquirRL: Automating Attack Discovery on Blockchain Incentive Mechanisms with Deep Reinforcement Learning
Incentive mechanisms are central to the functionality of permissionless blockchains: they incentivize participants to run and secure the underlying consensus protocol.
Cryptography and Security
Using GANs for Sharing Networked Time Series Data: Challenges, Initial Promise, and Open Questions
By shedding light on the promise and challenges, we hope our work can rekindle the conversation on workflows for data sharing.
Practical Low Latency Proof of Work Consensus
Bitcoin is the first fully-decentralized permissionless blockchain protocol to achieve a high level of security, but at the expense of poor throughput and latency.
Distributed, Parallel, and Cluster Computing Cryptography and Security Networking and Internet Architecture
InfoGAN-CR and ModelCentrality: Self-supervised Model Training and Selection for Disentangling GANs
Disentangled generative models map a latent code vector to a target space, while enforcing that a subset of the learned latent codes are interpretable and associated with distinct properties of the target distribution.
PacGAN: The power of two samples in generative adversarial networks
Generative adversarial networks (GANs) are innovative techniques for learning generative models of complex data distributions from samples.
Deanonymization in the Bitcoin P2P Network
Recent attacks on Bitcoin's peer-to-peer (P2P) network demonstrated that its transaction-flooding protocols, which are used to ensure network consistency, may enable user deanonymization---the linkage of a user's IP address with her pseudonym in the Bitcoin network.
Dandelion: Redesigning the Bitcoin Network for Anonymity
We propose a simple networking policy called Dandelion, which achieves nearly-optimal anonymity guarantees at minimal cost to the network's utility.
Cryptography and Security Information Theory Information Theory
Building a RAPPOR with the Unknown: Privacy-Preserving Learning of Associations and Data Dictionaries
Techniques based on randomized response enable the collection of potentially sensitive data from clients in a privacy-preserving manner with strong local differential privacy guarantees.
Cryptography and Security
Spy vs. Spy: Rumor Source Obfuscation
Whether for fear of judgment or personal endangerment, it is crucial to keep anonymous the identity of the user who initially posted a sensitive message.
