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.
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 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.
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.
Optimizes electric aircraft deployment for Canadian aviation to reduce emissions.
problem Limited fleet capacity and operational structure hinder electric aircraft transition.
method Multi-period mixed-integer linear programming (MILP) framework.
result Electric aircraft can reduce emissions by over 70% within five years.
Review of efficient neural networks for TinyML on resource-constrained devices.
problem Resource constraints on ultra-low power MCUs for deep learning models.
method Model compression, quantization, low-rank factorization, model pruning, hardware acceleration, algorithm-architecture co-design.
result Optimized neural network architectures for minimal resource utilization on MCUs.
Improved deep learning model deployment on tiny MCUs with mixed-precision quantization.
problem Memory limitations prevent accurate deployment of DNN models on tiny MCUs.
method Automated mixed-precision quantization using Reinforcement Learning for MCU constraints.
result Mixed-precision models achieve high accuracy with uniform quantization policies.
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.
Foundation models outperform supervised methods in time series forecasting across various operational regimes.
problem Lack of domain-specific training and ongoing maintenance in supervised learning for time series forecasting.
method Evaluation of foundation models against standard supervised approaches across four operational regimes: periodic, physically constrained, stochastic, and demand forecasting.
result Foundation models are optimal for cold-start or long-tail scenarios and perform well in domains with transferable periodic structures.
Edge language models show bias over time, especially on resource-constrained devices.
problem Bias in edge language models on resource-constrained devices.
method Comparative analysis of text-based bias across edge, cloud, and desktop environments; optimized Llama-2 model on Raspberry Pi 4; feedback loop mechanism to correct bias.
result Llama-2 on Raspberry Pi 4 shows 43.23% and 21.89% more bias over time compared to cloud and desktop models.
This paper presents a novel end-to-end methodology for enabling the deployment of low-error deep networks on microcontrollers. To fit the memory and computational limitations of resource-constrained edge-devices, we exploit mixed low-bitwidth compression, featuring 8, 4 or 2-bit uniform quantization, and we model the i…
Algorithm mitigates performance loss in constrained reinforcement learning with model misspecification.
problem Performance loss in reinforcement learning policies due to model misspecification in constrained control systems.
method Proposes an algorithm to handle constrained model misspecification in continuous control systems.
result Algorithm successfully mitigates performance loss in real-world reinforcement learning tasks.
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.
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.
New approach optimizes sales process for B2B businesses.
problem Optimizing the sales process for B2B businesses.
method Causal Predictive Optimization and Generation with three layers: prediction, optimization, and serving.
result Significant wins over legacy systems in LinkedIn implementation.
New framework for robust regularization under uncertain data distributions.
problem Addressing ill-posed inverse problems and statistical estimation under distributional uncertainty.
method Distributionally robust optimal regularization using convex duality.
result Identifies robust regularizers that remain effective under data distributional perturbations.
The increasing deployment of machine learning as well as legal regulations such as EU's GDPR cause a need for user-friendly explanations of decisions proposed by machine learning models. Counterfactual explanations are considered as one of the most popular techniques to explain a specific decision of a model. While the…
A number of results have recently demonstrated the benefits of incorporating various constraints when training deep architectures in vision and machine learning. The advantages range from guarantees for statistical generalization to better accuracy to compression. But support for general constraints within widely used …
Safe learning of stochastic dynamics with safety constraints.
problem Learning controlled stochastic dynamics with safety constraints.
method Iterative expansion of a safe control set using kernel-based confidence bounds.
result The method ensures safe exploration and efficient estimation of system dynamics.
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.
In many real-world reinforcement learning (RL) problems, besides optimizing the main objective function, an agent must concurrently avoid violating a number of constraints. In particular, besides optimizing performance it is crucial to guarantee the safety of an agent during training as well as deployment (e.g. a robot…
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…
Developing classification algorithms that are fair with respect to sensitive attributes of the data has become an important problem due to the growing deployment of classification algorithms in various social contexts. Several recent works have focused on fairness with respect to a specific metric, modeled the correspo…
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.
New research shows fairness in machine learning can sometimes make disadvantaged groups worse off.
problem The impact of fairness constraints in machine learning on different groups.
method Unified, population-level (Bayes) framework for binary classification under prevalent group fairness notions.
result Fairness in machine learning can lead to leveling down, making one or both groups worse off.
In order to scale transaction rates for deployment across the global web, many cryptocurrencies have deployed so-called "Layer-2" networks of private payment channels. An idealized payment network behaves like a Credit Network, a model for transactions across a network of bilateral trust relationships. Credit Networks …
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…
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.
A Bayesian factor graph reduced to normal form consists in the interconnection of diverter units (or equal constraint units) and Single-Input/Single-Output (SISO) blocks. In this framework localized adaptation rules are explicitly derived from a constrained maximum likelihood (ML) formulation and from a minimum KL-dive…
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.
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.
A new RL model ensures safe learning in uncertain environments.
problem Safe reinforcement learning in uncertain, partially observable environments.
method Lyapunov-based uncertainty quantification and Transformers for memory.
result Significant improvement in safety and optimality in grid-world tasks.
A geometric theory explains loss functions for robust representation learning.
problem Treats robustness, domain adaptation, and sensor drift as separate literatures.
method Estimates covariance Sigma_task and uses it to pin Jacobian penalties.
result Proves optimality and necessity of range coverage for penalty matrices.
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.
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.
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.
Using reinforcement learning to learn control policies is a challenge when the task is complex with potentially long horizons. Ensuring adequate but safe exploration is also crucial for controlling physical systems. In this paper, we use temporal logic to facilitate specification and learning of complex tasks. We combi…
Improved RL policies from offline data with relaxed BC constraints.
problem Overestimation bias in offline RL due to lack of interaction with environment.
method Introducing a policy constraint via behavioural cloning (BC) and adjusting the balance between RL and BC.
result Refined policies outperform baseline and match/exceed complex alternatives.
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…
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.
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 …
MPC framework reduces execution costs and schedule deviations in trading.
problem Executing large orders in markets under time and liquidity constraints.
method Model Predictive Control (MPC) framework balancing order completion, market impact, and opportunity cost.
result Significant reductions in slippage and schedule shortfall compared to benchmarks.
Method adapts frozen models for few-shot tasks without training.
problem Deployment constraints limit model updates, necessitating new adaptation methods.
method Exponential tilting of latent distribution for inference.
result Method outperforms parameter-update methods across benchmarks.
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.
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.
Decomposes bias in linear models under demographic parity constraints.
problem Understanding and quantifying bias in linear models under fairness constraints.
method Post-processing framework to decompose bias into direct and indirect components.
result Analytical characterization of how demographic parity reshapes model coefficients.
We study the problem of multi-agent reinforcement learning (MARL) with adaptivity constraints -- a new problem motivated by real-world applications where deployments of new policies are costly and the number of policy updates must be minimized. For two-player zero-sum Markov Games, we design a (policy) elimination base…