Search Results for author:
Found 66 papers, 8 papers with code
Constrained Language Generation with Discrete Diffusion Models
Constraints are critical in text generation as LLM outputs are often unreliable when it comes to ensuring generated outputs adhere to user defined instruction or general safety guidelines.
Global-Decision-Focused Neural ODEs for Proactive Grid Resilience Management
Extreme hazard events such as wildfires and hurricanes increasingly threaten power systems, causing widespread outages and disrupting critical services.
Simultaneous Multi-Robot Motion Planning with Projected Diffusion Models
Recent advances in diffusion models hold significant potential in robotics, enabling the generation of diverse and smooth trajectories directly from raw representations of the environment.
Multi-Agent Path Finding in Continuous Spaces with Projected Diffusion Models
To overcome this limitation, this work proposes a novel approach that integrates constrained optimization with diffusion models for MAPF in continuous spaces.
Differential Privacy Overview and Fundamental Techniques
This chapter is meant to be part of the book "Differential Privacy in Artificial Intelligence: From Theory to Practice" and provides an introduction to Differential Privacy.
Learning to Optimize meets Neural-ODE: Real-Time, Stability-Constrained AC OPF
Recent developments in applying machine learning to address Alternating Current Optimal Power Flow (AC OPF) problems have demonstrated significant potential in providing close to optimal solutions for generator dispatch in near real-time.
End-to-End Optimization and Learning of Fair Court Schedules
There is thus a need for fair criminal court pretrial scheduling systems that account for defendants' preferences and availability, but the collection of such data poses logistical challenges.
Learning To Solve Differential Equation Constrained Optimization Problems
Differential equations (DE) constrained optimization plays a critical role in numerous scientific and engineering fields, including energy systems, aerospace engineering, ecology, and finance, where optimal configurations or control strategies must be determined for systems governed by ordinary or stochastic differential equations.
Learning Joint Models of Prediction and Optimization
The Predict-Then-Optimize framework uses machine learning models to predict unknown parameters of an optimization problem from exogenous features before solving.
Fairness Issues and Mitigations in (Differentially Private) Socio-Demographic Data Processes
Statistical agencies rely on sampling techniques to collect socio-demographic data crucial for policy-making and resource allocation.
Speculative Diffusion Decoding: Accelerating Language Generation through Diffusion
Speculative decoding has emerged as a widely adopted method to accelerate large language model inference without sacrificing the quality of the model outputs.
Differentially Private Data Release on Graphs: Inefficiencies and Unfairness
The goal of this paper is to characterize the impact of DP on bias and unfairness in the context of releasing information about networks, taking a departure from previous work which has studied these effects in the context of private population counts release (such as in the U. S. Census).
The Data Minimization Principle in Machine Learning
The principle of data minimization aims to reduce the amount of data collected, processed or retained to minimize the potential for misuse, unauthorized access, or data breaches.
Low-rank finetuning for LLMs: A fairness perspective
Low-rank approximation techniques have become the de facto standard for fine-tuning Large Language Models (LLMs) due to their reduced computational and memory requirements.
Metric Learning to Accelerate Convergence of Operator Splitting Methods for Differentiable Parametric Programming
Recent work has shown a variety of ways in which machine learning can be used to accelerate the solution of constrained optimization problems.
Learning Constrained Optimization with Deep Augmented Lagrangian Methods
Learning to Optimize (LtO) is a problem setting in which a machine learning (ML) model is trained to emulate a constrained optimization solver.
End-to-End Learning for Fair Multiobjective Optimization Under Uncertainty
Many decision processes in artificial intelligence and operations research are modeled by parametric optimization problems whose defining parameters are unknown and must be inferred from observable data.
Learning Fair Ranking Policies via Differentiable Optimization of Ordered Weighted Averages
Learning to Rank (LTR) is one of the most widely used machine learning applications.
Disparate Impact on Group Accuracy of Linearization for Private Inference
Ensuring privacy-preserving inference on cryptographically secure data is a well-known computational challenge.
Constrained Synthesis with Projected Diffusion Models
This paper introduces an approach to endow generative diffusion processes the ability to satisfy and certify compliance with constraints and physical principles.
Analyzing and Enhancing the Backward-Pass Convergence of Unrolled Optimization
The integration of constrained optimization models as components in deep networks has led to promising advances on many specialized learning tasks.
On The Fairness Impacts of Hardware Selection in Machine Learning
In the machine learning ecosystem, hardware selection is often regarded as a mere utility, overshadowed by the spotlight on algorithms and data.
Predict-Then-Optimize by Proxy: Learning Joint Models of Prediction and Optimization
This paper proposes an alternative method, in which optimal solutions are learned directly from the observable features by predictive models.
Price-Aware Deep Learning for Electricity Markets
While deep learning gradually penetrates operational planning, its inherent prediction errors may significantly affect electricity prices.
Decision-Focused Learning: Foundations, State of the Art, Benchmark and Future Opportunities
This paper presents a comprehensive review of DFL, providing an in-depth analysis of both gradient-based and gradient-free techniques used to combine ML and constrained optimization.
FairDP: Certified Fairness with Differential Privacy
This paper introduces FairDP, a novel training mechanism designed to provide group fairness certification for the trained model's decisions, along with a differential privacy (DP) guarantee to protect training data.
On the Fairness Impacts of Private Ensembles Models
The Private Aggregation of Teacher Ensembles (PATE) is a machine learning framework that enables the creation of private models through the combination of multiple "teacher" models and a "student" model.
Personalized Privacy Auditing and Optimization at Test Time
A number of learning models used in consequential domains, such as to assist in legal, banking, hiring, and healthcare decisions, make use of potentially sensitive users' information to carry out inference.
Context-Aware Differential Privacy for Language Modeling
The remarkable ability of language models (LMs) has also brought challenges at the interface of AI and security.
Backpropagation of Unrolled Solvers with Folded Optimization
A central challenge in this setting is backpropagation through the solution of an optimization problem, which typically lacks a closed form.
Privacy and Bias Analysis of Disclosure Avoidance Systems
The results show that, contrary to popular beliefs, traditional differential privacy techniques may be superior in terms of accuracy and fairness to differential private counterparts of widely used DA mechanisms.
Fairness Increases Adversarial Vulnerability
The remarkable performance of deep learning models and their applications in consequential domains (e. g., facial recognition) introduces important challenges at the intersection of equity and security.
Differentiable Model Selection for Ensemble Learning
Model selection is a strategy aimed at creating accurate and robust models.
Gradient-Enhanced Physics-Informed Neural Networks for Power Systems Operational Support
The application of deep learning methods to speed up the resolution of challenging power flow problems has recently shown very encouraging results.
Pruning has a disparate impact on model accuracy
Network pruning is a widely-used compression technique that is able to significantly scale down overparameterized models with minimal loss of accuracy.
SF-PATE: Scalable, Fair, and Private Aggregation of Teacher Ensembles
A key characteristic of the proposed model is to enable the adoption of off-the-selves and non-private fair models to create a privacy-preserving and fair model.
Differential Privacy and Fairness in Decisions and Learning Tasks: A Survey
This paper surveys recent work in the intersection of differential privacy (DP) and fairness.
Deadwooding: Robust Global Pruning for Deep Neural Networks
The ability of Deep Neural Networks to approximate highly complex functions is key to their success.
Differentially-Private Heat and Electricity Markets Coordination
Sector coordination between heat and electricity systems has been identified has an energy-efficient and cost-effective way to transition towards a more sustainable energy system.
Post-processing of Differentially Private Data: A Fairness Perspective
Post-processing immunity is a fundamental property of differential privacy: it enables arbitrary data-independent transformations to differentially private outputs without affecting their privacy guarantees.
Differentially Private Empirical Risk Minimization under the Fairness Lens
However, it was recently observed that DP learning systems may exacerbate bias and unfairness for different groups of individuals.
Towards Understanding the Unreasonable Effectiveness of Learning AC-OPF Solutions
Optimal Power Flow (OPF) is a fundamental problem in power systems.
End-to-end Learning for Fair Ranking Systems
The end-to-end SPOFR framework includes a constrained optimization sub-model and produces ranking policies that are guaranteed to satisfy fairness constraints while allowing for fine control of the fairness-utility tradeoff.
Fast Approximations for Job Shop Scheduling: A Lagrangian Dual Deep Learning Method
The Jobs shop Scheduling Problem (JSP) is a canonical combinatorial optimization problem that is routinely solved for a variety of industrial purposes.
A Fairness Analysis on Private Aggregation of Teacher Ensembles
The Private Aggregation of Teacher Ensembles (PATE) is an important private machine learning framework.
Differentially Empirical Risk Minimization under the Fairness Lens
However, it was recently observed that DP learning systems may exacerbate bias and unfairness for different groups of individuals.
Learning Hard Optimization Problems: A Data Generation Perspective
Optimization problems are ubiquitous in our societies and are present in almost every segment of the economy.
A Privacy-Preserving and Trustable Multi-agent Learning Framework
Distributed multi-agent learning enables agents to cooperatively train a model without requiring to share their datasets.
Decision Making with Differential Privacy under a Fairness Lens
Agencies, such as the U. S. Census Bureau, release data sets and statistics about groups of individuals that are used as input to a number of critical decision processes.
End-to-End Constrained Optimization Learning: A Survey
This paper surveys the recent attempts at leveraging machine learning to solve constrained optimization problems.
Load Encoding for Learning AC-OPF
The AC Optimal Power Flow (AC-OPF) problem is a core building block in electrical transmission system.
Bias and Variance of Post-processing in Differential Privacy
Moreover, when the feasible region is convex, a widely adopted class of post-processing steps is also guaranteed to improve accuracy.
Differentially Private and Fair Deep Learning: A Lagrangian Dual Approach
A critical concern in data-driven decision making is to build models whose outcomes do not discriminate against some demographic groups, including gender, ethnicity, or age.
High-Fidelity Machine Learning Approximations of Large-Scale Optimal Power Flow
It is non-convex and NP-hard, and computationally challenging for large-scale power systems.
BIG-bench Machine Learning
Vocal Bursts Intensity Prediction
Differential Privacy of Hierarchical Census Data: An Optimization Approach
To address them, this paper presents a novel differential-privacy mechanism for releasing hierarchical counts of individuals.
Differentially Private Convex Optimization with Feasibility Guarantees
This paper develops a novel differentially private framework to solve convex optimization problems with sensitive optimization data and complex physical or operational constraints.
Lagrangian Duality for Constrained Deep Learning
In energy domains, the combination of Lagrangian duality and deep learning can be used to obtain state-of-the-art results to predict optimal power flows, in energy systems, and optimal compressor settings, in gas networks.
Bilevel Optimization for Differentially Private Optimization in Energy Systems
This paper studies how to apply differential privacy to constrained optimization problems whose inputs are sensitive.
Predicting AC Optimal Power Flows: Combining Deep Learning and Lagrangian Dual Methods
The Optimal Power Flow (OPF) problem is a fundamental building block for the optimization of electrical power systems.
Privacy-Preserving Obfuscation of Critical Infrastructure Networks
The paper studies how to release data about a critical infrastructure network (e. g., the power network or a transportation network) without disclosing sensitive information that can be exploited by malevolent agents, while preserving the realism of the network.
Differential Privacy for Power Grid Obfuscation
To address these concerns, this paper presents a novel differential privacy mechanism that guarantees AC-feasibility and largely preserves the fidelity of the obfuscated network.
OptStream: Releasing Time Series Privately
Then, the perturbation module adds noise to the sampled data points to guarantee privacy.
A Realistic Dataset for the Smart Home Device Scheduling Problem for DCOPs
The field of Distributed Constraint Optimization has gained momentum in recent years thanks to its ability to address various applications related to multi-agent cooperation.
Solving DCOPs with Distributed Large Neighborhood Search
The field of Distributed Constraint Optimization has gained momentum in recent years, thanks to its ability to address various applications related to multi-agent cooperation.
Accelerating Exact and Approximate Inference for (Distributed) Discrete Optimization with GPUs
Discrete optimization is a central problem in artificial intelligence.
Distributed Constraint Optimization Problems and Applications: A Survey
The field of Multi-Agent System (MAS) is an active area of research within Artificial Intelligence, with an increasingly important impact in industrial and other real-world applications.
