arXiv research

Confidence-based deferral works well in many scenarios but fails in specific cases.

Confidence-based filtering reveals latent structure in diffusion models.

Entropy-based decoding improves DLM sampling efficiency.

Efficiently solves exploration-exploitation in LQR using Lagrangian relaxation.

We present a confidence-based single-layer feed-forward learning algorithm SPIRAL (Spike Regularized Adaptive Learning) relying on an encoding of activation spikes. We adaptively update a weight vector relying on confidence estimates and activation offsets relative to previous activity. We regularize updates proportion…

While deep learning-based classification is generally tackled using standardized approaches, a wide variety of techniques are employed for regression. In computer vision, one particularly popular such technique is that of confidence-based regression, which entails predicting a confidence value for each input-target pai…

CAdam optimizes online learning by adapting to distribution shifts and noise.

A new algorithm reduces suboptimal arm selection in correlated bandits.

Audio source separation is the process of separating a mixture (e.g. a pop band recording) into isolated sounds from individual sources (e.g. just the lead vocals). Deep learning models are the state-of-the-art in source separation, given that the mixture to be separated is similar to the mixtures the deep model was tr…

New algorithm reduces pricing error by a factor of T^2/3.

DO-IQS recovers optimal stopping region from expert trajectories, addressing specific challenges.

Imitation learning (IL) aims to learn an optimal policy from demonstrations. However, such demonstrations are often imperfect since collecting optimal ones is costly. To effectively learn from imperfect demonstrations, we propose a novel approach that utilizes confidence scores, which describe the quality of demonstrat…

Optimal learning for parametric prophet inequalities with exponential-type distributions

Estimates rewards from a demonstrator's learning process.

New GLB algorithm handles non-stationary data with forgetting.

Study optimal control in unknown nonlinear systems with near-optimal regret bound.

Study improves fraud detection in e-commerce with a stacked model combining CNNs, GNNs, and confidence gating.

Study online learning in MDPs with aggregate bandit feedback, achieving low regret in both stochastic and adversarial settings.

A new algorithm for learning from functional data across multiple machines.

Unified hybrid RL algorithm improves online RL performance with offline data.

Algorithm maximizes rewards with a budget and giving up option.

The paper tackles adaptive questioning to classify candidate ability.

A new restart criterion for k-means++ improves clustering quality and adapts to data difficulty.

This paper proposes a novel policy for a group of agents to, individually as well as collectively, solve a multi armed bandit (MAB) problem. The policy relies solely on the information that an agent has obtained through sampling of the options on its own and through communication with neighbors. The option selection po…

New method learns fusion rules from few images using granular ball priors.

We propose a generic confidence-based approximation that can be plugged in and simplify the auto-regressive generation process with a proved convergence. We first assume that the priors of future samples can be generated in an independently and identically distributed (i.i.d.) manner using an efficient predictor. Given…

Lifelong learning with deep neural networks is well-known to suffer from catastrophic forgetting: the performance on previous tasks drastically degrades when learning a new task. To alleviate this effect, we propose to leverage a large stream of unlabeled data easily obtainable in the wild. In particular, we design a n…

Modern neural networks are very powerful predictive models, but they are often incapable of recognizing when their predictions may be wrong. Closely related to this is the task of out-of-distribution detection, where a network must determine whether or not an input is outside of the set on which it is expected to safel…

We endorse the idea, suggested in recent literature, that BitCoin prices are influenced by sentiment and confidence about the underlying technology; as a consequence, an excitement about the BitCoin system may propagate to BitCoin prices causing a Bubble effect, the presence of which is documented in several papers abo…

A new concept of confidence in learning is defined and analyzed.

Predicting properties of nodes in a graph is an important problem with applications in a variety of domains. Graph-based Semi-Supervised Learning (SSL) methods aim to address this problem by labeling a small subset of the nodes as seeds and then utilizing the graph structure to predict label scores for the rest of the …

We characterize a prevalent weakness of deep neural networks (DNNs)---overthinking---which occurs when a DNN can reach correct predictions before its final layer. Overthinking is computationally wasteful, and it can also be destructive when, by the final layer, a correct prediction changes into a misclassification. Und…

Hybrid quantum-classical model boosts S&P 500 prediction accuracy to 60.14%.

State-of-the-art, high capacity deep neural networks not only require large amounts of labelled training data, they are also highly susceptible to label errors in this data, typically resulting in large efforts and costs and therefore limiting the applicability of deep learning. To alleviate this issue, we propose a no…

SelectMix improves deep learning robustness against noisy labels.

HMS-BERT detects cyberbullying in multiple languages and labels.

A new method for making interpretable predictions by sequentially asking questions, faster and more efficient.

SMC analysis reveals key transient effects in macroeconomic ABM.

This research improves model interpretability and uncertainty estimation for deep learning models on non-iid data.

New truthful calibration errors improve model ranking in multiclass prediction.

New method improves model calibration by adjusting confidence based on prediction correctness.

CAT improves domain adaptation for fault diagnosis by calibrating teacher network predictions.

New attacks can infer model training membership using only label predictions, not confidence.

Examines algorithmic modeling across three cultures.

Playing repeated matrix games (RMG) while maximizing the cumulative returns is a basic method to evaluate multi-agent learning (MAL) algorithms. Previous work has shown that $UCB$, $M3$, $S$ or $Exp3$ algorithms have good behaviours on average in RMG. Besides, hedging algorithms have been shown to be effective on predi…

Meta-algorithm selection aims to choose the best algorithm selector for a given problem instance.

Proposes CLRS benchmark to evaluate algorithmic reasoning.

Combines multiple bandit algorithms to create a nearly optimal single algorithm.