Jaideep Ray

Jaideep Ray

Reinforcement learning with verifiable rewards (RLVR) replaces human preference labels with executable reward functions such as math answer checkers, JSON tool-call validators, and code unit-test harnesses. That makes the reward partly a software artifact: if the verifier is wrong, optimization can learn the bug. We study this failure mode with a lightweight verifier-fuzzing framework that generates adversarial completions, compares buggy and stricter reference verifiers, logs paired decisions, and reports false-positive, false-negative, disagreement, exploit, and uncertainty metrics.

Kevin Carlberg, Jaideep Ray, Bart van Bloemen Waanders

Implicit numerical integration of nonlinear ODEs requires solving a system of nonlinear algebraic equations at each time step. Each of these systems is often solved by a Newton-like method, which incurs a sequence of linear-system solves. Most model-reduction techniques for nonlinear ODEs exploit knowledge of system's spatial behavior to reduce the computational complexity of each linear-system solve. However, the number of linear-system solves for the reduced-order simulation often remains roughly the same as that for the full-order simulation. We propose exploiting knowledge of the model's temporal behavior to 1) forecast the unknown variable of the reduced-order system of nonlinear equations at future time steps, and 2) use this forecast as an initial guess for the Newton-like solver during the reduced-order-model simulation. To compute the forecast, we propose using the Gappy POD technique. The goal is to generate an a ccurate initial guess so that the Newton solver requires many fewer iterations to converge, thereby decreasing the number of lin ear-system solves in the reduced-order-model simulation.

Jaideep Ray

Production LLM systems increasingly require machine-readable outputs: JSON objects, typed traces, regex-constrained fields, and tool-call schemas. This paper targets on-device and low-cost small language model (SLM) deployments, where sub-3B models are attractive for privacy, latency, and commodity hardware but have limited capacity to satisfy schemas while solving tasks. The usual engineering assumption is that hard output constraints improve reliability without changing the underlying answer. We show that this assumption is unsafe for small models. We introduce \emph{constraint tax}, a measurement protocol for isolating the answer and executable-accuracy loss caused by structured-output constraints at fixed model, fixed task distribution, and fixed problem instances. Across 15,000 commodity-GPU generations with Qwen2.5-0.5B, Qwen2.5-1.5B, and SmolLM2-1.7B, hard answer-only schema decoding raises schema validity from 61.5\% to 100.0\%, but lowers answer accuracy from 19.7\% to 11.0\% and increases wrong-valid-schema outputs from 49.5\% to 88.9\%. The strongest industry analogue is a deterministic calendar tool-call task: Qwen2.5-1.5B achieves 91.5\% executable accuracy with prompt-only JSON but only 48.0\% under the same hard tool-call schema, while both modes are 100.0\% schema-valid. The error is semantic, not structural. We also show that the 3B boundary still pays a direct-schema tax and that delayed packaging supports a constructive design pattern: reason free, constrain late. The practical conclusion is direct: production systems should report schema validity, answer accuracy, executable accuracy, and wrong-valid-schema rate separately.

Connor Robertson, Cosmin Safta, Nicholson Collier et al.

Accurate calibration of stochastic agent-based models (ABMs) in epidemiology is crucial to make them useful in public health policy decisions and interventions. Traditional calibration methods, e.g., Markov Chain Monte Carlo (MCMC), that yield a probability density function for the parameters being calibrated, are often computationally expensive. When applied to ABMs which are highly parametrized, the calibration process becomes computationally infeasible. This paper investigates the utility of Stein Variational Inference (SVI) as an alternative calibration technique for stochastic epidemiological ABMs approximated by Gaussian process (GP) surrogates. SVI leverages gradient information to iteratively update a set of particles in the space of parameters being calibrated, offering potential advantages in scalability and efficiency for high-dimensional ABMs. The ensemble of particles yields a joint probability density function for the parameters and serves as the calibration. We compare the performance of SVI and MCMC in calibrating CityCOVID, a stochastic epidemiological ABM, focusing on predictive accuracy and calibration effectiveness. Our results demonstrate that SVI maintains predictive accuracy and calibration effectiveness comparable to MCMC, making it a viable alternative for complex epidemiological models. We also present the practical challenges of using a gradient-based calibration such as SVI which include careful tuning of hyperparameters and monitoring of the particle dynamics.

Jaideep Ray

Kubernetes offers a powerful orchestration platform for machine learning training, but memory management can be challenging due to specialized needs and resource constraints. This paper outlines how Kubernetes handles memory requests, limits, Quality of Service classes, and eviction policies for ML workloads, with special focus on GPU memory and ephemeral storage. Common pitfalls such as overcommitment, memory leaks, and ephemeral volume exhaustion are examined. We then provide best practices for stable, scalable memory utilization to help ML practitioners prevent out-of-memory events and ensure high-performance ML training pipelines.

Connor Robertson, Cosmin Safta, Nicholson Collier et al.

Agent-based models (ABM) provide an excellent framework for modeling outbreaks and interventions in epidemiology by explicitly accounting for diverse individual interactions and environments. However, these models are usually stochastic and highly parametrized, requiring precise calibration for predictive performance. When considering realistic numbers of agents and properly accounting for stochasticity, this high dimensional calibration can be computationally prohibitive. This paper presents a random forest based surrogate modeling technique to accelerate the evaluation of ABMs and demonstrates its use to calibrate an epidemiological ABM named CityCOVID via Markov chain Monte Carlo (MCMC). The technique is first outlined in the context of CityCOVID's quantities of interest, namely hospitalizations and deaths, by exploring dimensionality reduction via temporal decomposition with principal component analysis (PCA) and via sensitivity analysis. The calibration problem is then presented and samples are generated to best match COVID-19 hospitalization and death numbers in Chicago from March to June in 2020. These results are compared with previous approximate Bayesian calibration (IMABC) results and their predictive performance is analyzed showing improved performance with a reduction in computation.