papers

Publications (11)

stat.ML2026

Decomposition-Based Modular Conformal Prediction for Two-Stage Modeling

William Zhang, Saurabh Amin, Georgia Perakis

Conformal prediction offers finite-sample coverage guarantees under minimal assumptions. However, existing methods treat the entire modeling process as a black box, overlooking opp…

cs.DS2026

Approximation Algorithms for Inventory Problems with Decomposable Submodular Ordering Costs

Retsef Levi, Georgia Perakis, Emily Zhang

This paper develops an approximation algorithm for the submodular joint replenishment problem (SJRP) under a broad family of decomposable submodular ordering cost functions. In the…

cs.LG2025

CoRe: Coherency Regularization for Hierarchical Time Series

Rares Cristian, Pavithra Harhsa, Georgia Perakis +1

Hierarchical time series forecasting presents unique challenges, particularly when dealing with noisy data that may not perfectly adhere to aggregation constraints. This paper intr…

econ.GN2019

Data Analytics in Operations Management: A Review

Velibor V. Mišić, Georgia Perakis

Research in operations management has traditionally focused on models for understanding, mostly at a strategic level, how firms should operate. Spurred by the growing availability…

cs.LG2025

Efficient End-to-End Learning for Decision-Making: A Meta-Optimization Approach

Rares Cristian, Pavithra Harsha, Georgia Perakis +1

End-to-end learning has become a widely applicable and studied problem in training predictive ML models to be aware of their impact on downstream decision-making tasks. These end-t…

cs.AI2025

Causal LLM Routing: End-to-End Regret Minimization from Observational Data

Asterios Tsiourvas, Wei Sun, Georgia Perakis

LLM routing aims to select the most appropriate model for each query, balancing competing performance metrics such as accuracy and cost across a pool of language models. Prior appr…

math.OC2022

Optimizing Objective Functions from Trained ReLU Neural Networks via Sampling

Georgia Perakis, Asterios Tsiourvas

This paper introduces scalable, sampling-based algorithms that optimize trained neural networks with ReLU activations. We first propose an iterative algorithm that takes advantage…

cs.LG2025

Aligning Learning and Endogenous Decision-Making

Rares Cristian, Pavithra Harsha, Georgia Perakis +1

Many of the observations we make are biased by our decisions. For instance, the demand of items is impacted by the prices set, and online checkout choices are influenced by the ass…

math.OC2025

Tight Mixed-Integer Optimization Formulations for Prescriptive Trees

Max Biggs, Georgia Perakis

We focus on modeling the relationship between an input feature vector and the predicted outcome of a trained decision tree using mixed-integer optimization. This can be used in man…

stat.ML2024

Heterogeneous Treatment Effects in Panel Data

Retsef Levi, Elisabeth Paulson, Georgia Perakis +1

We address a core problem in causal inference: estimating heterogeneous treatment effects using panel data with general treatment patterns. Many existing methods either do not util…

cs.LG2024

Inter-Series Transformer: Attending to Products in Time Series Forecasting

Rares Cristian, Pavithra Harsha, Clemente Ocejo +4

Time series forecasting is an important task in many fields ranging from supply chain management to weather forecasting. Recently, Transformer neural network architectures have sho…