Publication

Multi-agent Learning with Privacy Guarantees

Related concepts (33)

Graph Chatbot

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.

Loss function

In mathematical optimization and decision theory, a loss function or cost function (sometimes also called an error function) is a function that maps an event or values of one or more variables onto a real number intuitively representing some "cost" associated with the event. An optimization problem seeks to minimize a loss function. An objective function is either a loss function or its opposite (in specific domains, variously called a reward function, a profit function, a utility function, a fitness function, etc.

Privacy law

Privacy law is the body of law that deals with the regulating, storing, and using of personally identifiable information, personal healthcare information, and financial information of individuals, which can be collected by governments, public or private organisations, or other individuals. It also applies in the commercial sector to things like trade secrets and the liability that directors, officers, and employees have when handing sensitive information.

Risk

In simple terms, risk is the possibility of something bad happening. Risk involves uncertainty about the effects/implications of an activity with respect to something that humans value (such as health, well-being, wealth, property or the environment), often focusing on negative, undesirable consequences. Many different definitions have been proposed. The international standard definition of risk for common understanding in different applications is "effect of uncertainty on objectives".

Distributed artificial intelligence

Distributed Artificial Intelligence (DAI) also called Decentralized Artificial Intelligence is a subfield of artificial intelligence research dedicated to the development of distributed solutions for problems. DAI is closely related to and a predecessor of the field of multi-agent systems. Multi-agent systems and distributed problem solving are the two main DAI approaches. There are numerous applications and tools. Distributed Artificial Intelligence (DAI) is an approach to solving complex learning, planning, and decision-making problems.

Right to privacy

The right to privacy is an element of various legal traditions that intends to restrain governmental and private actions that threaten the privacy of individuals. Over 150 national constitutions mention the right to privacy. On 10 December 1948, the United Nations General Assembly adopted the Universal Declaration of Human Rights (UDHR), originally written to guarantee individual rights of everyone everywhere; while right to privacy does not appear in the document, many interpret this through Article 12, which states: "No one shall be subjected to arbitrary interference with his privacy, family, home or correspondence, nor to attacks upon his honour and reputation.

Deep reinforcement learning

Deep reinforcement learning (deep RL) is a subfield of machine learning that combines reinforcement learning (RL) and deep learning. RL considers the problem of a computational agent learning to make decisions by trial and error. Deep RL incorporates deep learning into the solution, allowing agents to make decisions from unstructured input data without manual engineering of the state space. Deep RL algorithms are able to take in very large inputs (e.g.

Supervised learning

Supervised learning (SL) is a paradigm in machine learning where input objects (for example, a vector of predictor variables) and a desired output value (also known as human-labeled supervisory signal) train a model. The training data is processed, building a function that maps new data on expected output values. An optimal scenario will allow for the algorithm to correctly determine output values for unseen instances. This requires the learning algorithm to generalize from the training data to unseen situations in a "reasonable" way (see inductive bias).

Mean squared error

In statistics, the mean squared error (MSE) or mean squared deviation (MSD) of an estimator (of a procedure for estimating an unobserved quantity) measures the average of the squares of the errors—that is, the average squared difference between the estimated values and the actual value. MSE is a risk function, corresponding to the expected value of the squared error loss. The fact that MSE is almost always strictly positive (and not zero) is because of randomness or because the estimator does not account for information that could produce a more accurate estimate.

Privacy

Privacy (UK, US) is the ability of an individual or group to seclude themselves or information about themselves, and thereby express themselves selectively. The domain of privacy partially overlaps with security, which can include the concepts of appropriate use and protection of information. Privacy may also take the form of bodily integrity. There have been many different conceptions of privacy throughout history. Most cultures recognize the right of an individual to withhold aspects of their personal lives from public record.

Risk aversion

In economics and finance, risk aversion is the tendency of people to prefer outcomes with low uncertainty to those outcomes with high uncertainty, even if the average outcome of the latter is equal to or higher in monetary value than the more certain outcome. Risk aversion explains the inclination to agree to a situation with a more predictable, but possibly lower payoff, rather than another situation with a highly unpredictable, but possibly higher payoff.