Search Results for author:
Found 27 papers, 5 papers with code
Towards hyperparameter-free optimization with differential privacy
Differential privacy (DP) is a privacy-preserving paradigm that protects the training data when training deep learning models.
Tokens for Learning, Tokens for Unlearning: Mitigating Membership Inference Attacks in Large Language Models via Dual-Purpose Training
Large language models (LLMs) have become the backbone of modern natural language processing but pose privacy concerns about leaking sensitive training data.
Semiparametric Bayesian Difference-in-Differences
The second method is a double robust Bayesian procedure that adjusts the prior distribution of the conditional mean function and subsequently corrects the posterior distribution of the resulting ATT.
Technical Report for Soccernet 2023 -- Dense Video Captioning
In the task of dense video captioning of Soccernet dataset, we propose to generate a video caption of each soccer action and locate the timestamp of the caption.
Physics-Aware Combinatorial Assembly Sequence Planning using Data-free Action Masking
In the end, we apply the proposed method to Lego assembly with more than 250 3D structures.
Nl2Hltl2Plan: Scaling Up Natural Language Understanding for Multi-Robots Through Hierarchical Temporal Logic Task Representation
To enable non-experts to specify long-horizon, multi-robot collaborative tasks, language models are increasingly used to translate natural language commands into formal specifications.
DPDR: Gradient Decomposition and Reconstruction for Differentially Private Deep Learning
Third, the model is updated with the gradient reconstructed from recycled common knowledge and noisy incremental information.
Clip Body and Tail Separately: High Probability Guarantees for DPSGD with Heavy Tails
However, recent studies have shown that the gradients in deep learning exhibit a heavy-tail phenomenon, that is, the tails of the gradient have infinite variance, which may lead to excessive clipping loss to the gradients with existing DPSGD mechanisms.
KoReA-SFL: Knowledge Replay-based Split Federated Learning Against Catastrophic Forgetting
To avoid catastrophic forgetting, the main server of KoReA-SFL selects multiple assistant devices for knowledge replay according to the training data distribution of each server-side branch-model portion.
Quasi-Bayesian Estimation and Inference with Control Functions
We consider a quasi-Bayesian method that combines a frequentist estimation in the first stage and a Bayesian estimation/inference approach in the second stage.
PCDP-SGD: Improving the Convergence of Differentially Private SGD via Projection in Advance
We prove that pre-projection enhances the convergence of DP-SGD by reducing the dependence of clipping error and bias to a fraction of the top gradient eigenspace, and in theory, limits cross-client variance to improve the convergence under heterogeneous federation.
AdapterFL: Adaptive Heterogeneous Federated Learning for Resource-constrained Mobile Computing Systems
On the one hand, to achieve model training in all the diverse clients, mobile computing systems can only use small low-performance models for collaborative learning.
Zero redundancy distributed learning with differential privacy
Deep learning using large models have achieved great success in a wide range of domains.
On the accuracy and efficiency of group-wise clipping in differentially private optimization
Recent advances have substantially improved the accuracy, memory cost, and training speed of differentially private (DP) deep learning, especially on large vision and language models with millions to billions of parameters.
Coupling public and private gradient provably helps optimization
The success of large neural networks is crucially determined by the availability of data.
SoccerNet 2023 Challenges Results
More information on the tasks, challenges, and leaderboards are available on https://www. soccer-net. org.
A Lightweight and Transferable Design for Robust LEGO Manipulation
Experiments demonstrate that the EOAT can reliably manipulate Lego bricks and the learning framework can effectively and safely improve the manipulation performance to a 100% success rate.
Decomposition-based Hierarchical Task Allocation and Planning for Multi-Robots under Hierarchical Temporal Logic Specifications
Our approach was experimentally applied to domains of navigation and manipulation.
Proactive Human-Robot Co-Assembly: Leveraging Human Intention Prediction and Robust Safe Control
Second, it is difficult to ensure interactive safety due to uncertainty in human behaviors.
GUARD: A Safe Reinforcement Learning Benchmark
Due to the diversity of algorithms and tasks, it remains difficult to compare existing safe RL algorithms.
Double Robust Bayesian Inference on Average Treatment Effects
We prove asymptotic equivalence of our Bayesian procedure and efficient frequentist ATE estimators by establishing a new semiparametric Bernstein-von Mises theorem under double robustness; i. e., the lack of smoothness of conditional mean functions can be compensated by high regularity of the propensity score and vice versa.
PrivateRec: Differentially Private Training and Serving for Federated News Recommendation
Collecting and training over sensitive personal data raise severe privacy concerns in personalized recommendation systems, and federated learning can potentially alleviate the problem by training models over decentralized user data. However, a theoretically private solution in both the training and serving stages of federated recommendation is essential but still lacking. Furthermore, naively applying differential privacy (DP) to the two stages in federated recommendation would fail to achieve a satisfactory trade-off between privacy and utility due to the high-dimensional characteristics of model gradients and hidden representations. In this work, we propose a federated news recommendation method for achieving a better utility in model training and online serving under a DP guarantee. We first clarify the DP definition over behavior data for each round in the life-circle of federated recommendation systems. Next, we propose a privacy-preserving online serving mechanism under this definition based on the idea of decomposing user embeddings with public basic vectors and perturbing the lower-dimensional combination coefficients.
No One Left Behind: Inclusive Federated Learning over Heterogeneous Devices
In this way, all the clients can participate in the model learning in FL, and the final model can be big and powerful enough.
Efficient-FedRec: Efficient Federated Learning Framework for Privacy-Preserving News Recommendation
However, the computation and communication cost of directly learning many existing news recommendation models in a federated way are unacceptable for user clients.
Data Efficient Human Intention Prediction: Leveraging Neural Network Verification and Expert Guidance
Predicting human intention is critical to facilitating safe and efficient human-robot collaboration (HRC).
FLAME: Differentially Private Federated Learning in the Shuffle Model
In this work, by leveraging the \textit{privacy amplification} effect in the recently proposed shuffle model of differential privacy, we achieve the best of two worlds, i. e., accuracy in the curator model and strong privacy without relying on any trusted party.
FedSel: Federated SGD under Local Differential Privacy with Top-k Dimension Selection
To prevent privacy leakages from gradients that are calculated on users' sensitive data, local differential privacy (LDP) has been considered as a privacy guarantee in federated SGD recently.
