New method avoids redundancy in spectral embeddings.
problem Redundant coordinates in spectral dimensionality reduction.
method Introduces unpredictability constraints to avoid redundancy.
result Significantly more informative and compact representations.
Paper tackles unpredictable feature evolution in learning.
problem Learning with unpredictable feature evolution.
method Proposes PUFE method to fill incomplete overlapping period and formulate as matrix completion problem. Uses ensemble method to incorporate old and new feature spaces.
result Theoretical and experimental validation shows PUFE method can always follow the best base models.
BEGAN-CS prevents mode collapse in GANs by adding a latent-space constraint.
problem Mode collapse in BEGAN during training.
method Introducing a latent-space constraint in the loss function of BEGAN.
result BEGAN-CS improves training stability and suppresses mode collapse.
The study compares DLS method with machine learning for cricket match result prediction.
problem Improving accuracy of Duckworth-Lewis-Stern method for cricket match result prediction.
method Comparison of Duckworth-Lewis-Stern method with various supervised learning algorithms and optimization of DLS resource table.
result Development of Unpredictability Index to rank nations based on unpredictability in ODI matches.
Mechanical devices such as engines, vehicles, aircrafts, etc., are typically instrumented with numerous sensors to capture the behavior and health of the machine. However, there are often external factors or variables which are not captured by sensors leading to time-series which are inherently unpredictable. For insta…
New method for predicting paths of unpredictable objects with high confidence.
problem Need for dependable uncertainty estimates in motion planning with diverse unpredictable objects.
method Blend online conformal prediction, multiple time series techniques, and heteroscedasticity addressing.
result Simultaneous forecasting bands that cover entire paths with high probability.
MPC outperforms reactive budgeting in non-stationary return environments.
problem Optimizing budget allocation under non-stationary returns.
method Receding-horizon Model Predictive Control (MPC) compared to reactive policies.
result MPC consistently outperforms reactive budgeting when return dynamics are predictable.
Self-balancing sampler improves sampling efficiency and unpredictability.
problem Efficient and unpredictable sampling in various applications.
method Adaptive biasing of sampling probabilities to achieve faster convergence and unpredictability.
result Self-balancing sampler converges at O(n−1) rate, outperforming IID sampling. Gradient descent with large steps leads to chaotic parameter space and unpredictable outcomes.
problem Understanding the behavior of gradient descent with large step sizes in matrix factorization.
method Analyzing the fractal structure of the parameter space and deriving critical step sizes for convergence.
result Gradient descent with large steps exhibits chaotic behavior and sensitivity to initialization, creating a fractal boundary between converging and diverging minimizers.
Generative models with memory improve temporal data prediction.
problem Modeling temporal data with long-range dependencies.
method Generative Temporal Models augmented with external memory systems within variational inference.
result These models outperform existing models like LSTMs on tasks with sparse, long-term dependencies.
The Sornette-Ide differential equation of herding and rational trader behaviour together with very small random noise is shown to lead to crashes or bubbles where the price change goes to infinity after an unpredictable time. About 100 time steps before this singularity, a few predictable roughly log-periodic oscillati…
PredictaBoard benchmarks LLM score predictors to assess their ability to anticipate errors.
problem Inconsistent performance of LLMs in common sense reasoning tasks.
method Collaborative benchmarking framework evaluating pairs of LLMs and assessors using rejection rate at different tolerance errors.
result Highlights the need to evaluate predictability alongside performance for safer AI systems.
New method improves inference for discrete diffusion models, achieving better quality and efficiency.
problem High dimensionality of discrete diffusion models causes inference challenges.
method Developed high-order numerical inference schemes for discrete diffusion models.
result Second-order accuracy of the θ-Trapezoidal method in KL divergence. Deep RL for safe, multi-agent driving policies.
problem Safe negotiation with other road users in autonomous driving.
method Policy gradient iterations, decomposed into desires and constraints, hierarchical temporal abstraction.
result Significant reduction in gradient variance for safer driving policies.
Autotune automates hyperparameter tuning for machine learning models.
problem Hyperparameter tuning challenges in machine learning models.
method Derivative-free optimization framework combining specialized sampling and search methods.
result Significantly improved models over default settings with minimal user interaction.
Vroom optimizes in unpredictable conditions without derivatives.
problem Optimizing in non-stationary, adversarial environments.
method Zeroth-order online learning with vanishing regret.
result Achieves favorable rates in stochastic settings.
Paper controls type I error in text classification despite data distortion.
problem Data distortion in open online platforms leads to misclassification.
method Uses Neyman-Pearson (NP) classification paradigm to minimize type I error.
result NP methods control type I error on test data despite data distortion.
Paper analyzes how weather data improves solar power prediction.
problem Predicting the unpredictability of solar power generation.
method Examined the impact of weather data on photovoltaic power prediction.
result Weather data significantly improves photovoltaic power prediction accuracy.
New evaluation scheme shows existing methods are unreliable for out-of-distribution detection.
problem Evaluating out-of-distribution samples in deep learning models.
method Introducing OD-test, a three-dataset evaluation scheme.
result Existing methods are unreliable for real-world applications of high-dimensional images.
Study curvatures of diffeomorphisms on non-orientable surfaces.
problem Computing curvatures of measure-preserving diffeomorphisms on non-orientable surfaces.
method Extending Arnold and Lukatskii's approach, computing curvatures and asymptotics.
result Computed curvatures and asymptotics for the Klein bottle and real projective plane.
Optimizes trading in markets with unpredictable price impacts.
problem Optimizing trading strategies in markets with stochastic price impacts.
method Singular perturbation methods to approximate optimal control problem.
result Proves approximations are accurate to specified order using sub- and super-solutions.
Study identifies a Strategic Gap in market efficiency due to AI-driven timing and complexity in disclosure.
problem Market inefficiency due to structural influence of disclosure timing and complexity.
method Introduces Autonomous Disclosure Regulator, a multi-node AI framework to audit disclosure complexity and unpredictability.
result Companies use confusing language and unpredictable timing to slow down market learning, creating a 60% Structural Gap.
Predictability enables efficient parallelization of nonlinear models.
problem Understanding which nonlinear state space models can be efficiently parallelized.
method Established a relationship between system dynamics and optimization problem conditioning, quantified by the largest Lyapunov exponent.
result Predictable systems can be evaluated in O((logT)2) time, improving over conventional sequential approaches. We prove results on bounded solutions to backward stochastic equations driven by random measures. Those bounded BSDE solutions are then applied to solve different stochastic optimization problems with exponential utility in models where the underlying filtration is noncontinuous. This includes results on portfolio opti…
Modeling financial chaos with market makers' risk appetite.
problem Unpredictable price changes in financial markets.
method Using Hamiltonian approach with anharmonic oscillators and nonlinear coupling.
result Market makers' risk appetite determines chaotic dynamics in financial markets.
A new measure for traffic safety reduces variability in fatal crash data.
problem Unpredictable clusters in fatal crash data reduce traffic safety measurement accuracy.
method Introduced a fatal point concept and a rounding error method to detect it.
result The proposed measure is not significantly affected by cluster variability.
This dissertation uses deep reinforcement learning to improve drone flight control.
problem Inadequate traditional control methods for unpredictable CPS interactions.
method Developed a full solution stack for neuro-flight controllers using deep neural networks.
result Reinforcement learning enables training neural network controllers for stable and precise flight.
Algorithmic stablecoins optimize monetary policy to balance price stability.
problem Persistent inflation from centralized monetary policy.
method Propose and study a rule-based monetary policy model for algorithmic stablecoins.
result Optimal trade-off between price stability and supply stability.
Paper predicts stock prices using ML and human intelligence.
problem Uncertainty in stock price prediction.
method ML models (LSTM, ARIMA, CNN-LSTM, GRU, LSTM-GRU) augmented with Superforecasters predictions.
result Superforecasters' predictions improve stock price prediction accuracy.
Paper develops a model-based RL framework for portfolio optimization in financial markets.
problem Complex, non-Gaussian environment dynamics in financial markets.
method Heavy-tailed preserving normalizing flows for environment simulation; model-based reinforcement learning framework.
result Proposed method outperforms in various financial markets, especially during the pandemic.
Deep RL agent improves lane changing in unpredictable traffic.
problem Uncertainty in other drivers' behaviors and safety vs agility trade-off.
method Developed a deep reinforcement learning agent in a simulated highway environment.
result Significantly better performance in noisy environments compared to heuristic methods.
Many complex systems exhibit extreme events far more often than expected for a normal distribution. This work examines how self-similar bursts of activity across several orders of magnitude can emerge from first principles in systems that adapt to information. Surprising connections are found between two apparently unr…
Paper tackles RL for power grid topology optimization.
problem Managing large action spaces in growing power networks.
method Hierarchical multi-agent reinforcement learning (MARL) framework.
result MARL framework outperforms single-agent RL methods.
Graph conformal prediction predicts future power outages with high confidence.
problem Accurately predicting future power outages to enable rapid recovery.
method Developed a graph conformal prediction method for quarter-hourly outage data.
result Graph conformal prediction method delivers accurate prediction regions for future outage numbers.
New framework ensures valid uncertainty estimates for any data stream changes.
problem Challenges of distribution shifts and adversarial actors in real-world data streams.
method Leveraging Blackwell approachability from game theory, the framework guarantees calibrated uncertainties for any compact space.
result Improves calibration and decision-making for energy systems.
ExpO regularizes models to improve their explainability.
problem Improving the interpretability of black-box models.
method ExpO is a hybridization of regularization and post-hoc explanation systems.
result Post-hoc explanations for ExpO-regularized models have better explanation quality.
Stock prices predicted using a Transformer model.
problem Predicting stock prices with high accuracy.
method Multivariate forecasting using a mutated Transformer model.
result Transformer model outperformed traditional methods in stock price prediction.
Asynchronous cooperative learning rules ensure all agents converge to correct hypothesis.
problem Cooperative learning in networks with unreliable communication.
method Proposed robust cooperative learning rule for weak communication networks.
result All agents' beliefs exponentially decay to the correct hypothesis.
New CDC scheme avoids intergenerational subsidies, offering better outcomes.
problem Intergenerational cross-subsidies in UK CDC schemes.
method Collective-Drawdown CDC approach using explicit insurance contracts.
result Better pension outcomes with no intergenerational cross-subsidies.
In complex systems, crucial parameters are often subject to unpredictable changes in time. Climate, biological evolution and networks provide numerous examples for such non-stationarities. In many cases, improved statistical models are urgently called for. In a general setting, we study systems of correlated quantities…
Improved cover song detection with neural networks.
problem Identifying cover songs from original recordings.
method Siamese Convolutional Neural Networks trained on cover song audio clips.
result Mean precision@1 of 65% over mini-batches, significantly outperforming random guessing.
This work optimizes DNN inference for energy-harvesting devices by compressing and selectively executing neural network exits.
problem Inference delays and energy inefficiency in energy-harvesting devices.
method Developed a power trace-aware and exit-guided network compression algorithm for multi-exit neural networks.
result Superior accuracy and reduced latency compared to state-of-the-art techniques.
Study bank salvage model with stochastic impulse controls to minimize costs.
problem Minimize total cost of saving a bank from default with unpredictable default time.
method Impulse stochastic controls to address the bank's default risk.
result Unique viscosity solution exists for the QVI, with Lipschitz and Holder continuity properties.
We study the market impact of a meta-order in the framework of the Minority Game. This amounts to studying the response of the market when introducing a trader who buys or sells a fixed amount h for a finite time T. This perturbation introduces statistical arbitrages that traders exploit by adapting their trading strat…
Study optimizes investment strategies in volatile markets using machine learning and Bayesian techniques.
problem Enhancing portfolio management in volatile markets.
method Market segmentation into ten volatility-based states, real-time asset allocation adjustments using Bayesian Markov switching model.
result Dynamic portfolio achieves significantly higher risk-adjusted returns and total returns.
We consider a model in which a trader aims to maximize expected risk-adjusted profit while trading a single security. In our model, each price change is a linear combination of observed factors, impact resulting from the trader's current and prior activity, and unpredictable random effects. The trader must learn coeffi…
We investigate the dynamics of a trust game on a mixed population where individuals with the role of buyers are forced to play against a predetermined number of sellers, whom they choose dynamically. Agents with the role of sellers are also allowed to adapt the level of value for money of their products, based on payof…
We identify spectral conditions for reliable neural probe interpretation.
problem Unreliable performance of linear probes in interpreting neural representations.
method Formalized Spectral Identifiability Principle (SIP) based on eigengap and Fisher error.
result Reliability of neural probes depends on the eigengap relative to Fisher estimation error.