Bitcoin fails to prove safe haven status during pandemic.
problem Determining if Bitcoin is a reliable safe haven asset during crises.
method Quantile correlations of Bitcoin with S&P500, VIX, and gold.
result Gold is a better safe haven during crises, not Bitcoin.
Safe imitation learning with a safety layer for flexible training.
problem Flexible yet safe imitation learning for complex tasks.
method Theory and modular method with a safety layer for continuous policy, adversarial training, and worst-case safety guarantees.
result Robustness advantage of safety layer during training compared to test time.
Classifier-based AI safety gates fail in self-improvement, even with advanced verification methods.
problem Maintaining reliable oversight of AI systems as they improve over iterations.
method Comprehensive empirical testing on neural controllers and MuJoCo benchmarks, using various classifiers and verification methods.
result Classifier-based safety gates fail in maintaining reliable oversight, even with advanced verification methods.
BagCert efficiently certifies robustness against adversarial patches on image classifiers.
problem Adversarial patches pose a threat to autonomous systems' perception component.
method BagCert combines model architecture and certification procedure for efficient inference.
result BagCert certifies 10,000 examples in 43 seconds on a single GPU, achieving 86% clean and 60% certified accuracy against 5x5 patches.
Framework trains safe agents avoiding deceptive behavior.
problem Training safe agents from unsafe incentives.
method Formal settings, causal influence analysis, maximizing non-mediated effects.
result Agents avoid manipulating delicate state for rewards.
We consider rules for discarding predictors in lasso regression and related problems, for computational efficiency. El Ghaoui et al (2010) propose "SAFE" rules that guarantee that a coefficient will be zero in the solution, based on the inner products of each predictor with the outcome. In this paper we propose strong …
This work tackles force control for contact-rich manipulation tasks with rigid robots using RL.
problem Challenges in working with real robotic hardware, especially position-controlled robots.
method Combines RL with traditional force control techniques, implementing parallel position/force control and admittance control.
result Validated methods on both simulation and real robot (UR3 e-series) for force control.
Safe-FinRL uses DRL for high-frequency stock trading, reducing bias and variance.
problem Challenges in applying DRL to high-frequency stock trading, especially bias and variance issues.
method Safe-FinRL separates financial time series into near-stationary short environments and uses Trace-SAC with a general retrace operator.
result Safe-FinRL reduces bias and variance significantly in near-stationary financial environments.
Safe reinforcement learning tackles safety constraints with linear approximations.
problem Ensuring safety in reinforcement learning without violating constraints.
method Modeling safety as a linear cost function, developing SLUCB-QVI and RSLUCB-QVI algorithms for MDPs with linear function approximation.
result Achieved a nearly optimal regret bound for safe reinforcement learning, matching state-of-the-art unsafe algorithms.
FSPT identifies training space to prevent ML model extrapolation.
problem Lack of training data leads to unreliable predictions outside the training space.
method FSPT: Feature Space Partitioning Tree to identify training space.
result Strong relationship between model performance and FSPT score.
This primer tackles biases in machine learning for image analysis, proposing solutions.
problem Causal and statistical biases in machine learning methods for image analysis.
method Introduction of causal and statistical structures that induce failure, highlighting two problems: no fair lunch and subgroup separability.
result Current fair representation learning methods fail to solve these problems, suggesting new paths forward.
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.
Study best arm identification with safety constraints in bandit problems.
problem Real-world decision-making with safety constraints.
method Analyzed linear and monotonic reward and safety constraints, proposed algorithms.
result Guaranteed safe learning in both linear and general reward/safety constraint settings.
Fair ML systems can be safe ML systems by considering uncertainty.
problem Safety of data-driven decision systems is often neglected.
method Viewing ML systems as socio-technical, uncertainty-aware modeling.
result Fair models should be uncertainty-aware, e.g. through distributional regression.
Safe linear stochastic bandits ensure safe exploration with optimal regret.
problem Ensuring safe exploration in stochastic bandits while minimizing regret.
method Combining known safe arms with exploratory arms to safely expand the set of safe arms over time.
result The algorithm achieves an expected regret of O ( T log ( T ) ) O(\sqrt{T}\log (T)) O ( T log ( T )) . This work provides safety guarantees for iterative GP predictions.
problem Analytical intractability of uncertainty tracking in iterative GP predictions.
method Deriving formal probability error bounds for iterative GP predictions.
result Formal bounds ensure that GP trajectories lie within specified regions with high probability.
CoCoRL learns safe constraints from demonstrations with unknown rewards.
problem Learning safe constraints from demonstrations with different unknown rewards.
method Convex Constraint Learning for Reinforcement Learning (CoCoRL) constructs a convex safe set based on demonstrations.
result CoCoRL learns constraints that lead to safe driving behavior and can safely transfer to different tasks and environments.
SafePILCO is a Python tool for safe reinforcement learning.
problem Safe and efficient policy synthesis in reinforcement learning.
method Extends PILCO algorithm with safety features, implemented in Python.
result Safe and data-efficient policy synthesis achieved.
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.
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.
High dimensional regression benefits from sparsity promoting regularizations. Screening rules leverage the known sparsity of the solution by ignoring some variables in the optimization, hence speeding up solvers. When the procedure is proven not to discard features wrongly the rules are said to be \emph{safe}. In this …
We show that when a third party, the adversary, steps into the two-party setting (agent and operator) of safely interruptible reinforcement learning, a trade-off has to be made between the probability of following the optimal policy in the limit, and the probability of escaping a dangerous situation created by the adve…
Study on neural networks to identify redundancy issues in safe machine learning.
problem Identifying redundancy in neural network architectures for safe machine learning.
method Experiments with MNIST database using neural network classifiers.
result Underlines difficulties in using neural network classifiers for safe systems.
We study safe screening for metric learning. Distance metric learning can optimize a metric over a set of triplets, each one of which is defined by a pair of same class instances and an instance in a different class. However, the number of possible triplets is quite huge even for a small dataset. Our safe triplet scree…
Proposes a method to accelerate safe sequential learning using offline data.
problem Limited exploration due to disconnected safe regions and slow task learning.
method Safe transfer sequential learning using Gaussian processes and offline data.
result Enhances global exploration across multiple disjoint safe regions with lower data consumption.
Meta-learning priors improves safe Bayesian optimization.
problem Optimizing robot controllers under safety constraints.
method Meta-learning priors from offline data using F-PACOH.
result Meta-learned priors accelerate safe BO convergence.
Revel tackles safe exploration in RL with verified symbolic policies.
problem Computational infeasibility of verifying neural networks in RL learning loops.
method Two policy classes: neurosymbolic with approximate gradients and symbolic policies for efficient verification. Mirror descent over policies to safely update and project policies.
result Revel discovers policies that outperform prior approaches to verified exploration.
Safe exploration framework for IML algorithms.
problem Safe decision-making in IML without unsafe outcomes.
method Exploits Gaussian process prior to efficiently learn safe decisions.
result Outperforms other algorithms empirically.
ASE safely explores unknown MDPs with unknown dynamics, improving sample efficiency.
problem Balancing exploration and safety in unknown MDPs with stochastic dynamics.
method Exploits analogies between state-action pairs to safely learn near-optimal policies.
result Empirically improves sample efficiency compared to existing methods.
Safe reinforcement learning for autonomous vehicles using prediction constraints.
problem Safe reinforcement learning for safety-critical applications like autonomous vehicles.
method Use prediction to constrain exploration in reinforcement learning models.
result Successfully learned intersection handling behaviors on an autonomous vehicle.
Safe-House secures DeFi by limiting losses and enhancing security.
problem Ongoing hacks and security concerns in DeFi.
method Safe-House uses blockchain principles to secure asset movements.
result Safe-House limits maximum one-time loss to specified limits.
Machine learning algorithms are increasingly influencing our decisions and interacting with us in all parts of our daily lives. Therefore, just like for power plants, highways, and myriad other engineered sociotechnical systems, we must consider the safety of systems involving machine learning. In this paper, we first …
OSIL learns safe policies from unsafe demonstrations.
problem Offline safe imitation learning with implicit safety.
method Formulates CMDP, infers safety from non-preferred trajectories, learns cost model.
result OSIL learns safer policies without degrading reward performance.
Machine learning algorithms increasingly influence our decisions and interact with us in all parts of our daily lives. Therefore, just as we consider the safety of power plants, highways, and a variety of other engineered socio-technical systems, we must also take into account the safety of systems involving machine le…
We study the problem of safe learning and exploration in sequential control problems. The goal is to safely collect data samples from operating in an environment, in order to learn to achieve a challenging control goal (e.g., an agile maneuver close to a boundary). A central challenge in this setting is how to quantify…
The problem of learning a sparse model is conceptually interpreted as the process of identifying active features/samples and then optimizing the model over them. Recently introduced safe screening allows us to identify a part of non-active features/samples. So far, safe screening has been individually studied either fo…
A new screening rule 'dynamic Sasvi' improves sparse optimization speed.
problem Sparse optimization problem identification.
method Flexible framework based on Fenchel-Rockafellar duality for norm-regularized least squares.
result Dynamic Sasvi can eliminate more features and increase solver speed.
Safe autonomous decisions made with machine learning predictions using Conformal Decision Theory.
problem Safe decisions from imperfect machine learning predictions.
method Conformal Decision Theory framework for producing safe decisions.
result Safe decisions with provable statistical guarantees of low risk.
Crypto-assets perform better than gold as safe-havens during market crashes.
problem Evaluating safe-haven properties of crypto-assets and gold during the 2020 market crash.
method Comparative analysis of Crypto-assets (Tether, Cardano, Dogecoin, Bitcoin, Ethereum, Litecoin, Ripple) and gold for European indices.
result Tether, Cardano, and Dogecoin exhibited hedging properties similar to gold, while gold was not more efficient as a safe-haven.
Safe Bayesian optimization method using information theory.
problem Optimizing unknown functions while respecting safety constraints.
method Information-theoretic exploration criterion for continuous domains.
result The method learns the value of the safe optimum up to arbitrary precision.
Safe sample screening improves RSVM performance without sacrificing accuracy.
problem Improving RSVM performance under noisy conditions.
method Proposed two safe sample screening rules based on CCCP framework for RSVM.
result Significant reduction in computational time for RSVM.
Safe screening rules reduce computation time in logistic regression with ℓ 0 − ℓ 2 \ell_0-\ell_2 ℓ 0 − ℓ 2 regularization.
problem Efficiently solving logistic regression with many features and regularization.
method Screening rules based on Fenchel dual lower bounds of strong conic relaxations.
result A high percentage of features can be safely removed before solving, leading to substantial speed-up.
In high dimensional regression settings, sparsity enforcing penalties have proved useful to regularize the data-fitting term. A recently introduced technique called screening rules propose to ignore some variables in the optimization leveraging the expected sparsity of the solutions and consequently leading to faster s…
SAMBA improves safe reinforcement learning with active exploration metrics.
problem Safe reinforcement learning in dynamic systems.
method Combines probabilistic modelling, information theory, and statistics. Uses novel metrics for out-of-sample Gaussian process evaluation.
result Orders of magnitude reduction in samples and violations compared to state-of-the-art methods.
Safe-M 3 ^3 3 -UCRL learns safe policies for multi-agent systems with global constraints.
problem Global constraints in mean-field reinforcement learning for multi-agent systems.
method Safe-M 3 ^3 3 -UCRL uses epistemic uncertainty and log-barrier approach to ensure constraints satisfaction. result Safe-M 3 ^3 3 -UCRL learns safe policies for multi-agent systems with global constraints. Paper improves safe policy improvement with estimated baseline policy.
problem Unreliable batch Reinforcement Learning algorithms in real-world applications.
method Apply SPIBB algorithms with an estimated baseline policy.
result Safe policy improvement guarantees over true baseline without direct access.
During times of extreme market turmoil, it is acknowledged that there is a tendency towards "flight to safety". A strong (weak) safe haven is defined as an asset that has a significant positive (negative) return in periods where another asset is in distress, while hedge has to be negatively correlated (uncorrelated) on…
Adapts safe policies for exploration in high-risk settings.
problem Balancing safety and exploration in high-risk environments.
method Uses conformal calibration on a safe reference policy to determine aggressive action limits.
result Safe exploration improves performance without requiring model class identification or hyperparameter tuning.