A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
SecVM preserves user privacy in training SVMs for classification tasks.
Paper explores differential privacy in high-dimensional federated learning, tackling server trustworthiness and estimation.
Develops a new deep learning framework for privacy-preserving text representations.
Classical clients can verify quantum learning tasks efficiently.
CheckNet verifies neural network inference on untrusted devices.
As Machine Learning (ML) gets applied to security-critical or sensitive domains, there is a growing need for integrity and privacy for outsourced ML computations. A pragmatic solution comes from Trusted Execution Environments (TEEs), which use hardware and software protections to isolate sensitive computations from the…
New study shows non-interactive privacy model requires exponentially more data.
New method uses untrusted data for more precise causal analysis.
New algorithms learn from untrusted batches with improved efficiency.
Simplifies and optimizes learning from untrusted batches with structure.
Secure neural network inference on untrusted platforms using holographic reduced representations.
Machine learning on encrypted data has received a lot of attention thanks to recent breakthroughs in homomorphic encryption and secure multi-party computation. It allows outsourcing computation to untrusted servers without sacrificing privacy of sensitive data. We propose a practical framework to perform partially encr…
Lapse improves parameter servers by dynamically allocating parameters, achieving near-linear scaling.
A new scheme for private computation splits client data into shares for server operations.
In machine learning, classification models need to be trained in order to predict class labels. When the training data contains personal information about individuals, collecting training data becomes difficult due to privacy concerns. Local differential privacy is a definition to measure the individual privacy when th…
New algorithm for federated learning without a central server.
Distributed gradient descent (DGD) is an efficient way of implementing gradient descent (GD), especially for large data sets, by dividing the computation tasks into smaller subtasks and assigning to different computing servers (CSs) to be executed in parallel. In standard parallel execution, per-iteration waiting time …
Algorithm stabilizes queues in asymmetric systems with unknown service rates.
Corella protects client data privacy in multi-server learning with correlated queries.
LiuBei is a resilient ML algorithm that tolerates Byzantine workers and servers without trusting any component.
New method speeds up distributed linear regression.
Study privacy-utility trade-off in IoT time-series data sharing with RL.
This paper makes two contributions to Bayesian machine learning algorithms. Firstly, we propose stochastic natural gradient expectation propagation (SNEP), a novel alternative to expectation propagation (EP), a popular variational inference algorithm. SNEP is a black box variational algorithm, in that it does not requi…
Federated learning obtains a central model on the server by aggregating models trained locally on clients. As a result, federated learning does not require clients to upload their data to the server, thereby preserving the data privacy of the clients. One challenge in federated learning is to reduce the client-server c…
CSE-FSL reduces communication and storage costs in federated learning.
Machine Learning (ML) solutions are nowadays distributed, according to the so-called server/worker architecture. One server holds the model parameters while several workers train the model. Clearly, such architecture is prone to various types of component failures, which can be all encompassed within the spectrum of a …
New method reduces FL communication cost by leveraging server's side information.
Communication on heterogeneous edge networks is a fundamental bottleneck in Federated Learning (FL), restricting both model capacity and user participation. To address this issue, we introduce two novel strategies to reduce communication costs: (1) the use of lossy compression on the global model sent server-to-client;…
Detects backdoors in outsourced models by replicating training steps across multiple servers.
This paper improves privacy in federated learning without a trusted server.
This work provides bounds on generalization error and privacy leakage in federated learning.
Paper tackles federated linear bandit learning with AirComp for noisy channels.
Client-based machine learning uses mobile devices for computation, improving privacy and reducing data upload.
Paper proposes a GPU-based system for training massive deep learning models in ads systems.
DFedAvgM is a decentralized FedAvg with momentum for privacy and communication efficiency.
Paper improves communication in distributed optimization, reducing worker-to-server data exchanges.
We propose three new robust aggregation rules for distributed synchronous Stochastic Gradient Descent~(SGD) under a general Byzantine failure model. The attackers can arbitrarily manipulate the data transferred between the servers and the workers in the parameter server~(PS) architecture. We prove the Byzantine resilie…
This paper proposes a cooperative mechanism for mitigating the performance degradation due to non-independent-and-identically-distributed (non-IID) data in collaborative machine learning (ML), namely federated learning (FL), which trains an ML model using the rich data and computational resources of mobile clients with…
We propose a novel robust aggregation rule for distributed synchronous Stochastic Gradient Descent~(SGD) under a general Byzantine failure model. The attackers can arbitrarily manipulate the data transferred between the servers and the workers in the parameter server~(PS) architecture. We prove the Byzantine resilience…
Byzantine-resilient federated learning with local iterations and robust mean estimation.
The parameter server architecture is prevalently used for distributed deep learning. Each worker machine in a parameter server system trains the complete model, which leads to a hefty amount of network data transfer between workers and servers. We empirically observe that the data transfer has a non-negligible impact o…
Modern machine learning methods often require more data for training than a single expert can provide. Therefore, it has become a standard procedure to collect data from external sources, e.g. via crowdsourcing. Unfortunately, the quality of these sources is not always guaranteed. As additional complications, the data …
Access to sufficient annotated data is a common challenge in training deep neural networks on medical images. As annotating data is expensive and time-consuming, it is difficult for an individual medical center to reach large enough sample sizes to build their own, personalized models. As an alternative, data from all …
In this work, we propose a novel framework for privacy-preserving client-distributed machine learning. It is motivated by the desire to achieve differential privacy guarantees in the local model of privacy in a way that satisfies all systems constraints using asynchronous client-server communication and provides attrac…
In the edge computing paradigm, mobile devices offload the computational tasks to an edge server by routing the required data over the wireless network. The full potential of edge computing becomes realized only if a smart device selects the most appropriate server in terms of the latency and energy consumption, among …
Mix2FLD improves FL accuracy with FD, reducing convergence time.
Many machine learning systems rely on data collected in the wild from untrusted sources, exposing the learning algorithms to data poisoning. Attackers can inject malicious data in the training dataset to subvert the learning process, compromising the performance of the algorithm producing errors in a targeted or an ind…
Paper studies IPG method's robustness in noisy distributed linear regression.