Locally private online changepoint detection
Dec 6, 2021
Speakers
Tom Berrett
Speaker · 0 followers
About
We study online change point detection problems under the constraint of local differential privacy (LDP) where, in particular, the statistician does not have access to the raw data. As a concrete problem, we study a multivariate nonparametric regression problem. At each time point t, the raw data are assumed to be of the form (X_t, Y_t), where X_t is a d-dimensional feature vector and Y_t is a response variable. Our primary aim is to detect changes in the regression function m_t(x)=𝔼(Y_t |X_t=x) as soon as the change occurs. We provide algorithms which respect the LDP constraint, which control the false alarm probability, and which detect changes with a minimal (minimax rate-optimal) delay. To quantify the cost of privacy, we also present the optimal rate in the benchmark, non-private setting. These non-private results are also new to the literature and thus are interesting per se. In addition, we study the univariate mean online change point detection problem, under privacy constraints. This serves as the blueprint of studying more complicated private change point detection problems.We study online change point detection problems under the constraint of local differential privacy (LDP) where, in particular, the statistician does not have access to the raw data. As a concrete problem, we study a multivariate nonparametric regression problem. At each time point t, the raw data are assumed to be of the form (X_t, Y_t), where X_t is a d-dimensional feature vector and Y_t is a response variable. Our primary aim is to detect changes in the regression function m_t(x)=𝔼(Y_t |X_t=x…
Organizer
NeurIPS 2021
Account · 1.9k followers
About NeurIPS 2021
Neural Information Processing Systems (NeurIPS) is a multi-track machine learning and computational neuroscience conference that includes invited talks, demonstrations, symposia and oral and poster presentations of refereed papers. Following the conference, there are workshops which provide a less formal setting.
Like the format? Trust SlidesLive to capture your next event!
Professional recording and live streaming, delivered globally.
Sharing
Recommended Videos
Presentations on similar topic, category or speaker
Membership Inference Attacks on Natural Language Processing Classification Models
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Towards Enabling Meta-Learning from Target Models
Watch later
Su Lu, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Tailoring: encoding inductive biases by optimizing unsupervised objectives at prediction time
Watch later
Ferran Alet, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Row-clustering of a Point Process-valued Matrix
Watch later
Lihao Yin, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Conditioning Variational Gaussian Processes for Online Decision-making
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Towards Zero and Few-shot Knowledge-seeking Turn Detection in Task-orientated Dialogue Systems
Watch later
Di Jin, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%