New multi-spiral approach improves packaging of thick membranes.
problem Deploying thick membranes on curved surfaces efficiently.
method Multi-spiral folding approach with prismatic folding lines.
result Improved deployment performance of thick membranes on curved surfaces.
Operations is a key challenge in the domain of machine learning pipeline deployments involving monitoring and management of real-time prediction quality. Typically, metrics like accuracy, RMSE etc., are used to track the performance of models in deployment. However, these metrics cannot be calculated in production due …
MLDemon monitors ML systems post-deployment, improving reliability with real-time performance estimates and expert labels.
problem Ensuring reliability of machine learning systems post-deployment, especially when user inputs differ from training data.
method Integrates unlabeled and on-demand labeled data to monitor ML model performance in real-time, deciding when to acquire expert labels.
result Outperforms existing approaches in temporal datasets with diverse distribution drifts, providing theoretical optimality for distribution drifts.
Safe-DRFS selects features robust to covariate shifts for reliable performance.
problem Feature selection fails in diverse deployment environments.
method Safe-DRFS extends safe screening to distributionally robust settings under covariate shift.
result Safe-DRFS identifies a feature subset encompassing optimal subsets across distribution shifts.
A method for quickly determining deployment schedules that meet a given fuel cycle demand is presented here. This algorithm is fast enough to perform in situ within low-fidelity fuel cycle simulators. It uses Gaussian process regression models to predict the production curve as a function of time and the number of depl…
Automated framework optimizes DNN deployment on Arm CPUs.
problem Lack of globally optimised DNN deployment across software levels.
method Reinforcement Learning search for automated design space exploration.
result Up to 4x improvement in performance and 2x reduction in memory.
New CV method reduces bias in spatial prediction models.
problem Bias in standard cross-validation due to uneven sampling.
method Target-Weighted Cross-Validation (TWCV) framework.
result Weighted CV approaches reduce bias in prediction error.
Self-supervised policy adapts after deployment without rewards.
problem Generalizing reinforcement learning policies across different environments.
method Uses self-supervision to train policies in new environments without reward signals.
result Significant improvements in generalization across diverse environments.
Detects data drift and outliers affecting ML model performance over time.
problem Detecting distribution changes between training and deployment datasets for machine learning models.
method Nonparametrically tests model prediction confidence distributions for changes using Change Point Models (CPMs). Also uses nonparametric outlier methods.
result Demonstrates robustness of the method under various levels of drift class contamination.
Deployment-complete benchmarking assesses if evidence leads to consistent deployment actions.
problem Lack of clear evidence leading to consistent deployment actions.
method Introduces deployment-complete benchmarking to test if benchmark evidence determines deployment actions.
result Benchmark evidence must be complete for a claim to lead to a consistent deployment action.
Next generation of embedded Information and Communication Technology (ICT) systems are collaborative systems able to perform autonomous tasks. The remarkable expansion of the embedded ICT market, together with the rise and breakthroughs of Artificial Intelligence (AI), have put the focus on the Edge as it stands as one…
Paper optimizes training data distribution for better model performance across various deployment conditions.
problem Improving model accuracy when deployed with parameters far from training data.
method Developed adaptive algorithms based on bilevel or alternating optimization in the space of probability measures.
result Optimized training distributions lead to models with improved sample complexity and robustness to distribution shift.
GRAM enhances deep RL for reliable real-world deployment.
problem Generalizing deep RL across in-distribution and out-of-distribution scenarios.
method Introduces a robust adaptation module and a joint training pipeline.
result GRAM achieves strong generalization performance in simulations and hardware.
Underspecified ML models can behave unpredictably in real-world use.
problem ML models can fail in real-world deployment due to ambiguous predictors.
method Identified underspecification as the cause, showing it affects various ML domains.
result Underspecified models can behave differently in deployment domains.
Suitability filter detects model performance degradation in real-world deployment.
problem Ensuring model reliability in safety-critical domains without access to ground truth labels.
method Uses suitability signals to evaluate classifier performance on unlabeled user data.
result The suitability filter reliably detects performance deviations due to covariate shift.
Paper establishes lower bounds and optimal algorithms for deployment-efficient RL.
problem Deployment efficiency in reinforcement learning.
method Optimization with constraints, lower bounds, algorithms.
result Established optimal algorithms for deployment-efficient RL.
DUPLE tackles cross-deployment recognition in fiber-optic perimeter security with meta-learning.
problem Cross-deployment recognition challenges in fiber-optic perimeter security due to label scarcity and distribution shifts.
method DUPLE employs statistically guided meta-learning to enhance recognition robustness across unseen deployments.
result DUPLE consistently outperforms traditional and meta-learning baselines in cross-deployment DFOS benchmarks.
A framework to quantify deployment risk in ML systems, especially for rare states.
problem Under-supported rare states in ML models lead to unreliable performance in unseen data.
method Blind-Spot Mass (B_n(tau)) using Good-Turing unseen-species estimation.
result Identifies and quantifies the risk of under-supported states in ML models.
Deployment of machine learning (ML) algorithms in production for extended periods of time has uncovered new challenges such as monitoring and management of real-time prediction quality of a model in the absence of labels. However, such tracking is imperative to prevent catastrophic business outcomes resulting from inco…
New method optimizes language model performance for test-time strategies.
problem Mismatch between training objectives and test-time deployment of large language models.
method Tail-Extrapolated estimators to approximate best-of-N performance from limited training rollouts.
result Improved performance of best-of-N deployment across various models and datasets.
Machine learning (ML), especially deep learning is made possible by the availability of big data, enormous compute power and, often overlooked, development tools or frameworks. As the algorithms become mature and efficient, more and more ML inference is moving out of datacenters/cloud and deployed on edge devices. This…
A new method predicts stock ranking uncertainty to improve trading performance during regime shifts.
problem Ranking models fail during regime shifts, leading to suboptimal performance.
method Adapting DEUP to rankers, predicting rank displacement and uncertainty, and proposing a two-level deployment policy.
result The two-level deployment policy improves risk-adjusted performance and indicates DEUP adds value mainly as a tail-risk guard.
Framework for responsible LLM deployment with human involvement and decentralized technologies.
problem Challenges in deploying LLMs for high-stakes decisions, including data security and accountability.
method Interactive human involvement through multiple iterations, decentralized technologies, and automated auditing.
result Enhanced security and accountability in LLM deployment for financial decisions.
This paper reduces labeling costs for meta-learning in wireless systems.
problem Expensive labeling in meta-learning for wireless systems.
method Bayesian active task selection mechanism.
result Reduces the number of labeling steps required for meta-learning.
RTSCV detects unknown unknowns to improve model performance.
problem Model deficiency due to incomplete training data.
method Random Test Sampling and Cross-Validation (RTSCV) framework.
result Reduces performance gap by up to 41%.
Paper proposes efficient UAV placement for aerial base stations.
problem Efficient placement of UAVs as aerial base stations to serve varying traffic demand.
method Modeling UAV deployment as a non-cooperative game and using a learning-based algorithm to update UAV locations.
result Significant performance gains up to 52% and 74% in terms of throughput and dropped users compared to an optimized baseline algorithm.
The paper develops methods to reduce deployment risk under dynamic covariate shifts.
problem Reduction of deployment risk under dynamic covariate shifts.
method Time-domain Poincare inequality and Jacobian-velocity theorem to identify and control directional tangent energy.
result Drift-aligned tangent regularization (DTR) reduces risk volatility and directional gain in low-rank drift regimes.
The traditional paradigm for developing machine prognostics usually relies on generalization from data acquired in experiments under controlled conditions prior to deployment of the equipment. Detecting or predicting failures and estimating machine health in this way assumes that future field data will have a very simi…
RL research overhypes potential but lacks deployable solutions.
problem Current RL research overhypes potential and lacks deployable solutions.
method Identifies and critiques current RL research practices.
result Current RL research direction is unlikely to lead to practical, economically viable solutions.
The DoD needs a robust process to evaluate AI/ML model performance and robustness.
problem AI/ML models are brittle and nonrobust, posing risks in national security.
method Reviews AI/ML development process and best practices for evaluation.
result Recommendations for DoD evaluators to ensure robust AI/ML capabilities.
Survey of challenges and future directions in applying RL to real-world settings.
problem Challenges in deploying RL in practical settings due to limited interaction and changing environments.
method Analysis of RL system design, implementation, and continual improvement.
result Need for theory and methodology to bridge research and application gap.
CSA fills a gap in RLVR-trained LLM deployment by providing anytime-valid selective risk control.
problem Deployment of RLVR-trained LLMs in regulated organizations requires a safety certificate for every round without waiting for long-run averages.
method CSA uses a (test statistic, validity guarantee, deployment rule) framework to fill the gap, maintaining a Ville-type e-process per threshold on a Bonferroni grid.
result CSA provides the first anytime-valid selective risk control for RLVR-trained LLMs, matching the long-run average certification rate and satisfying pathwise validity and non-refusing deployment on every cell.
Automation of machine learning model development is increasingly becoming an established research area. While automated model selection and automated data pre-processing have been studied in depth, there is, however, a gap concerning automated model adaptation strategies when multiple strategies are available. Manually…
BREMEN optimizes policies offline with fewer data, achieving efficient deployment.
problem High cost of updating policies in real-world applications.
method Behavior-Regularized Model-ENsemble (BREMEN) algorithm for offline optimization.
result BREMEN achieves impressive deployment efficiency with 5-10 deployments, outperforming standard RL methods.
Algometrics analyzes how predictive models affect their own forecasts in algorithmic markets.
problem How predictive models affect their own forecasts in algorithmic markets.
method Introduces algometrics, a framework for time series with feedback, proving three results on deployment risk.
result Deployment risk cannot be identified from passive historical data alone, and historical rankings can invert under crowding.
SWIFT improves time series forecasting on edge devices with wavelet decomposition.
problem Efficient time series forecasting on resource-constrained devices.
method Wavelet decomposition, cross-band fusion, and shared linear mapping.
result SWIFT achieves state-of-the-art performance on multiple datasets.
New RL algorithm reduces deployment cost for linear function approximations.
problem Efficiently deploying new policies in RL with unknown rewards.
method Proposes an algorithm that minimizes trajectories needed for identifying optimal policies.
result Achieves optimal deployment complexity and sample complexity.
Paper proposes a graph model for optimal AP deployment in indoor optical wireless networks.
problem Challenges in deploying optical wireless networks due to LoS requirement and limited range.
method Graph modeling approach to identify minimum number of APs and their optimal locations.
result Optimal deployment of APs ensures connectivity and minimizes interference in indoor environments.
NEMO framework quantizes DNNs for efficient deployment.
problem Efficient deployment of quantized DNNs.
method Formal framework for quantizing DNN layers, focusing on IntegerDeployable representation.
result Quantized DNNs can be deployed using only integers.
Safe reinforcement learning framework using optimal transport for robustness.
problem Robustness and safety in deep reinforcement learning with limited data assumptions.
method Optimal transport perturbations to construct worst-case virtual state transitions.
result Significantly improved safety at deployment time compared to standard methods.
This research secures deployed sentiment analysis models by identifying and defending against attack vectors.
problem Securing deployed machine learning models, particularly sentiment analysis systems, from adversarial attacks.
method BAD (Build, Attack, Defend) Architecture, evaluating two implementations.
result Demonstrated a viable methodology for securing machine learning models in production.
We propose design guidelines for a probabilistic programming facility suitable for deployment as a part of a production software system. As a reference implementation, we introduce Infergo, a probabilistic programming facility for Go, a modern programming language of choice for server-side software development. We argu…
Orpheus simplifies deep learning deployment on edge devices.
problem Optimizing deep learning inference on edge devices for efficiency.
method Orpheus is a new framework with a small codebase, minimal dependencies, and easy integration.
result Preliminary results show the effectiveness of Orpheus for inference optimisations.
ML Compass helps organizations choose AI models that balance utility, cost, and compliance.
problem Selecting AI models that meet user utility, deployment costs, and compliance requirements.
method Develops ML Compass, a framework for constrained optimization over a capability-cost frontier, using internal measures and empirical data.
result ML Compass produces deployment-aware recommendations that differ from capability-only rankings, clarifying trade-offs between capability, cost, and safety.
Paper discusses challenges in deploying ML models for structural engineering.
problem Challenges in deploying machine learning models for structural engineering applications.
method Illustrates challenges through two examples, focusing on model overfitting, underspecification, training data representativeness, variable omission bias, and cross-validation.
result Highlights the importance of rigorous model validation techniques.
FlexServe simplifies deployment of PyTorch models as REST endpoints.
problem Lack of control over model evolution and strict security requirements in operational environments.
method Developed FlexServe, a library to deploy multi-model ensembles with flexible batching.
result Rapid deployment of PyTorch models without intermediate transformations.
Algorithm minimizes regret in predictive models influenced by their own predictions.
problem Finding near-optimal models under performativity with unknown shifts.
method Developed an algorithm that uses performative feedback to achieve low regret, scaling only with distribution shift complexity.
result Achieved regret bounds scaling with distribution shift complexity, not reward function complexity.
Amazon SageMaker Model Monitor detects drift in deployed ML models.
problem Ensuring high performance of ML models in production environments.
method Automatically detects data, concept, bias, and feature attribution drift in real-time.
result Maintains high quality models by providing alerts and corrective actions.