Redundancy in AI perception systems doesn't guarantee independent error occurrences.
problem Lack of direct statistical evidence of super-human automated driving performance.
method Investigated the effectiveness of redundancy in neural networks for independent error occurrences.
result Errors in neural networks for computer vision tasks are correlated, not independent.
Deep reinforcement learning methods attain super-human performance in a wide range of environments. Such methods are grossly inefficient, often taking orders of magnitudes more data than humans to achieve reasonable performance. We propose Neural Episodic Control: a deep reinforcement learning agent that is able to rap…
We introduce NoisyNet, a deep reinforcement learning agent with parametric noise added to its weights, and show that the induced stochasticity of the agent's policy can be used to aid efficient exploration. The parameters of the noise are learned with gradient descent along with the remaining network weights. NoisyNet …
Clinical AI models fail to transfer between sites due to site-specific practices.
problem Clinical AI models perform poorly at new sites.
method Identify and isolate site-specific clinical practices affecting data distribution.
result A potential solution to improve model transferability.
Modern reinforcement learning algorithms reach super-human performance on many board and video games, but they are sample inefficient, i.e. they typically require significantly more playing experience than humans to reach an equal performance level. To improve sample efficiency, an agent may build a model of the enviro…
Within the last decade, neural network based predictors have demonstrated impressive - and at times super-human - capabilities. This performance is often paid for with an intransparent prediction process and thus has sparked numerous contributions in the novel field of explainable artificial intelligence (XAI). In this…
AlphaZero reveals new chess concepts learnable by top experts.
problem Extracting and understanding hidden knowledge from AI systems.
method Proposed method to extract new chess concepts from AlphaZero.
result Top chess grandmasters show improvements in learning new concepts.
Paper presents a DRL framework for detecting and anticipating financial crises.
problem Detecting and adapting to financial crises using deep reinforcement learning.
method Two sub-networks, one for past performances and standard deviations, the other for contextual features. Adversarial training for robustness.
result Framework substantially outperforms traditional methods in detecting and anticipating crises.
Neural networks are achieving state of the art and sometimes super-human performance on learning tasks across a variety of domains. Whenever these problems require learning in a continual or sequential manner, however, neural networks suffer from the problem of catastrophic forgetting; they forget how to solve previous…
In recent years, reinforcement learning (RL) methods have been applied to model gameplay with great success, achieving super-human performance in various environments, such as Atari, Go, and Poker. However, those studies mostly focus on winning the game and have largely ignored the rich and complex human motivations, w…
Geometric approach improves probabilistic robustness in neural networks.
problem Widespread lack of robustness in deep neural networks to adversarial examples.
method Geometric view on Probabilistically Robust Learning (PRL) and introduction of new perimeters.
result Existence of solutions and properties of modified PRL models.
CollaQ improves multi-agent performance in StarCraft by 40% with fewer samples.
problem Limited generalization and high training rounds in multi-agent reinforcement learning.
method Formulates multi-agent collaboration as joint optimization on reward assignment, decomposes Q-function into self and interactive terms, and uses MARA loss.
result Improves win rate by 40% in StarCraft maps with same number of samples compared to state-of-the-art techniques.
Adversarial machine learning is a fast growing research area, which considers the scenarios when machine learning systems may face potential adversarial attackers, who intentionally synthesize input data to make a well-trained model to make mistake. It always involves a defending side, usually a classifier, and an atta…
Reinforcement learning has seen great advancements in the past five years. The successful introduction of deep learning in place of more traditional methods allowed reinforcement learning to scale to very complex domains achieving super-human performance in environments like the game of Go or numerous video games. Desp…
A grand challenge in machine learning is the development of computational algorithms that match or outperform humans in perceptual inference tasks that are complicated by nuisance variation. For instance, visual object recognition involves the unknown object position, orientation, and scale in object recognition while …
XPO enhances RLHF by encouraging diverse responses, offering improved sample efficiency.
problem Limited exploration in RLHF leads to suboptimal models and bottlenecks.
method XPO is a simple one-line change to DPO, introducing a novel exploration bonus.
result XPO achieves strong theoretical guarantees and promising empirical performance.
Access to high-quality education at scale is limited by the difficulty of providing student feedback on open-ended assignments in structured domains like computer programming, graphics, and short response questions. This problem has proven to be exceptionally difficult: for humans, it requires large amounts of manual w…
We report successful results from using deep learning neural networks (DLNNs) to learn, purely by observation, the behavior of profitable traders in an electronic market closely modelled on the limit-order-book (LOB) market mechanisms that are commonly found in the real-world global financial markets for equities (stoc…
New method uses MCTS only at test time for faster game learning.
problem High computational demands in game learning.
method Combines MCTS with TD learning agents for faster, reproducible agents.
result First learning-from-scratch agent to beat Edax up to level 7.
Deep Reinforcement Learning improves with Weighted Q-Learning to reduce bias and uncertainty.
problem Overestimation and high variance in Q-Learning cause learning algorithms to diverge in complex environments.
method Deep Weighted Q-Learning (Deep WQL) uses Dropout and Monte Carlo sampling to approximate WQL's weights and reduce bias.
result Deep WQL reduces bias and improves performance on benchmarks compared to existing methods.
This paper optimizes performative risk by focusing on convex properties and developing efficient algorithms.
problem Performative risk, the loss experienced by decision makers, is not optimized by stable models.
method Identifying convex properties of loss function and model-induced distribution shift, developing algorithms for optimization.
result Optimization of performative risk with better sample efficiency than generic methods.
Plug-in method improves performative prediction accuracy.
problem Learning under performative feedback with slow convergence rates.
method Plug-in performative optimization using models.
result Plug-in method can be superior to model-agnostic strategies.
We present a new methodology of computing incremental contribution for performance ratios for portfolio like Sharpe, Treynor, Calmar or Sterling ratios. Using Euler's homogeneous function theorem, we are able to decompose these performance ratios as a linear combination of individual modified performance ratios. This a…
The computation of convolution layers in deep neural networks typically rely on high performance routines that trade space for time by using additional memory (either for packing purposes or required as part of the algorithm) to improve performance. The problems with such an approach are two-fold. First, these routines…
New causal models perform poorly when evaluated on biased training sets.
problem Sample selection bias affects the evaluation of causal models' prediction performance.
method Re-evaluated prediction performance of causal models on a genetic perturbation data set, proposing a less-biased evaluation set.
result Causal models have similar or worse performance when evaluated on a less-biased set compared to standard association-based estimators.
A new framework for performative prediction robust to distributional misspecification.
problem Performative prediction models can be influenced by their own predictions, leading to suboptimal outcomes.
method Introduces distributionally robust performative prediction (DRPO) to approximate the true performative optimum (PO) robustly.
result DRPO provides provable guarantees as a robust approximation to the true PO when the nominal distribution map is misspecified.
Study compares Islamic banks' accounting and market performance.
problem Assessing the relationship between Islamic banks' accounting and market performance.
method Selected six Islamic banks, collected data from 2009-2013, used random-effect models.
result Superior accounting performance does not correlate with superior market performance.
The study evaluates AI model performance measures for medical use.
problem Selecting appropriate performance measures for AI models in medical practice.
method Assessed 32 performance measures across five domains for binary outcomes.
result 17 measures are both proper and reflect decision-analytic performance.
SHIFT framework identifies subgroups with large ML model performance decay.
problem Large model performance decay in subgroups when deployed.
method Subgroup-scanning Hierarchical Inference Framework (SHIFT) for performance drift.
result SHIFT identifies interpretable subgroups with large performance decay and suggests targeted actions to mitigate it.
New framework for predicting decisions that influence their own outcomes.
problem Predictions that affect the outcomes they predict, leading to undesirable distribution shift.
method Risk minimization framework combining statistics, game theory, and causality.
result Necessary and sufficient conditions for retraining to converge to a performatively stable point of minimal loss.
The paper explores how machine learning models can be learnable despite label shifts.
problem Learnability of binary classification models in the presence of label shifts.
method Developed a performative empirical risk function that is an unbiased estimate of the true risk on the shifted distribution.
result PAC-learnable hypothesis spaces remain PAC-learnable for performative scenarios.
New approach tackles decision-making under predictions that shape outcomes.
problem Challenges in learning optimal decision rules when predictions influence outcomes.
method Introduces performative omniprediction, a predictor that encodes optimal decision rules for multiple objectives.
result Efficient performative omnipredictors exist under a natural restriction of outcome performativity.
This paper extends performative prediction to nonlinear cases.
problem Performative prediction's effectiveness is limited by linear assumptions in real-world applications.
method Formulated a maximum margin approach loss function and extended it to nonlinear spaces using kernel methods.
result Derived conditions for performative stability in both linear and nonlinear cases.
Learn2Evaluate uses learning curves to estimate high-dimensional prediction performance.
problem Estimating test performance in high-dimensional data settings is challenging.
method Learn2Evaluate uses learning curves to estimate test performance at the total sample size.
result Learn2Evaluate provides a lower confidence bound for performance estimation.
New method improves consistency of reinforcement learning performance evaluations.
problem Inconsistent performance results in reinforcement learning due to flawed evaluation metrics.
method Proposes a new comprehensive evaluation methodology for reinforcement learning algorithms.
result Demonstrates improved reliability of performance measurements for reinforcement learning algorithms.
Machine learning predicts ship performance changes over time.
problem Estimating ship hydrodynamic performance over time.
method Machine learning methods (NL-PCR, NL-PLSR, probabilistic ANN) calibrated with in-service data.
result Probabilistic ANN model performs best in predicting ship performance changes.
Survey of performative prediction, a machine learning setup causing distribution shifts.
problem Machine learning models causing shifts in the environment they predict.
method Classification of performative prediction settings based on distribution map information.
result Introduction of new solution concepts and theoretical analyses.
Proposes a Siamese NN for algorithm selection focusing on alike performing instances.
problem Lack of effective meta-features for algorithm selection via meta-learning.
method Siamese Neural Network architecture with 'Algorithm-Performance Personas' concept.
result Proposed metric outperforms standard performance metrics in training sample selection.
MO-PaDGAN generates diverse, high-performance designs with multiple metrics.
problem Challenges in generating diverse, high-performance designs with multiple metrics.
method MO-PaDGAN uses a new Determinantal Point Processes based loss function for probabilistic modeling of diversity and performances.
result MO-PaDGAN expands the design space towards high-performance regions and generates new designs with high diversity and performances.
The paper explores conditions for predicting optimization performance.
problem Lack of formal theoretical guarantees linking prediction and optimization performance.
method Exploring conditions for asymptotic convergence and exact quantification of optimization performance.
result Explicit theoretical relationship between prediction and optimization performance.
Paper proposes GP-NAS-ensemble for fast neural architecture performance prediction.
problem Estimating neural network performance without training time-consuming evaluations.
method GP-NAS-ensemble framework using ensemble learning improvements.
result Ranked second in a NAS performance prediction challenge.
Proposes a new cross-validation method to estimate model performance.
problem The standard cross-validation method does not accurately estimate the performance of the recommended model.
method Develops a new random-effects model framework to improve naive cross-validation estimators.
result Proposed estimators outperform conventional and naive methods in estimating model performance.
Partially performative prediction studies how predictive models influence future data.
problem Distribution shift in predictive models due to endogenous and exogenous factors.
method Generalizing performative prediction to capture both endogenous and exogenous sources of distribution shift.
result Developed online analogues of performative stability and optimality for partially performative environments.
Paper analyzes impact of PRM on binary random variables and distribution shifts.
problem Impact of performative risk minimization on binary random variables and distribution shifts.
method Formulated two measures of impact, derived explicit formulas for full information, and provided estimators for partial information.
result PRM can have amplified side effects compared to methods that do not model data shift.
Proposes a method to select fair performance metrics through metric elicitation.
problem Choosing fair performance metrics in multiclass classification with multiple sensitive groups.
method Metric elicitation strategy that requires only relative preference feedback and is robust to noise.
result Elicits group-fair performance metrics for multiclass classification problems.
Paper establishes statistical inference for performative predictions.
problem Dynamic influence of predictions on their targets.
method End-to-end framework for estimation and inference under performativity.
result Established central limit theorem for performative settings.
Training deep learning models on mobile devices recently becomes possible, because of increasing computation power on mobile hardware and the advantages of enabling high user experiences. Most of the existing work on machine learning at mobile devices is focused on the inference of deep learning models (particularly co…
The performance of an organic photovoltaic device is intricately connected to its active layer morphology. This connection between the active layer and device performance is very expensive to evaluate, either experimentally or computationally. Hence, designing morphologies to achieve higher performances is non-trivial …