이기민 교수

Detecting test samples drawn sufficiently far away from the training distribution statistically or adversarially is a fundamental requirement for deploying a good classifier in many real-world machine learning applications. However, deep neural networks with the softmax classifier are known to produce highly overconfident posterior distributions even for such abnormal samples. In this paper, we propose a simple yet effective method for detecting any abnormal samples, which is applicable to any p

The problem of detecting whether a test sample is from in-distribution (i.e.,\ntraining distribution by a classifier) or out-of-distribution sufficiently\ndifferent from it arises in many real-world machine learning applications.\nHowever, the state-of-art deep neural networks are known to be highly\noverconfident in their predictions, i.e., do not distinguish in- and\nout-of-distributions. Recently, to handle this issue, several threshold-based\ndetectors have been proposed given pre-trained ne

Large-scale datasets may contain significant proportions of noisy (incorrect) class labels, and it is well-known that modern deep neural networks (DNNs) poorly generalize from such noisy training datasets. To mitigate the issue, we propose a novel inference method, termed Robust Generative classifier (RoG), applicable to any discriminative (e.g., softmax) neural classifier pre-trained on noisy datasets. In particular, we induce a generative classifier on top of hidden feature spaces of the pre-t

Deep reinforcement learning (RL) agents often fail to generalize to unseen environments (yet semantically similar to trained agents), particularly when they are trained on high-dimensional state spaces, such as images. In this paper, we propose a simple technique to improve a generalization ability of deep RL agents by introducing a randomized (convolutional) neural network that randomly perturbs input observations. It enables trained agents to adapt to new domains by learning robust features in

Deep reinforcement learning (RL) agents often fail to generalize to unseen environments (yet semantically similar to trained agents), particularly when they are trained on high-dimensional state spaces, such as images. In this paper, we propose a simple technique to improve a generalization ability of deep RL agents by introducing a randomized (convolutional) neural network that randomly perturbs input observations. It enables trained agents to adapt to new domains by learning robust features in

Off-policy deep reinforcement learning (RL) has been successful in a range of challenging domains. However, standard off-policy RL algorithms can suffer from several issues, such as instability in Q-learning and balancing exploration and exploitation. To mitigate these issues, we present SUNRISE, a simple unified ensemble method, which is compatible with various off-policy RL algorithms. SUNRISE integrates two key ingredients: (a) ensemble-based weighted Bellman backups, which re-weight target Q

Detecting test samples drawn sufficiently far away from the training distribution statistically or adversarially is a fundamental requirement for deploying a good classifier in many real-world machine learning applications. However, deep neural networks with the softmax classifier are known to produce highly overconfident posterior distributions even for such abnormal samples. In this paper, we propose a simple yet effective method for detecting any abnormal samples, which is applicable to any p

Deep generative models have shown impressive results in text-to-image synthesis. However, current text-to-image models often generate images that are inadequately aligned with text prompts. We propose a fine-tuning method for aligning such models using human feedback, comprising three stages. First, we collect human feedback assessing model output alignment from a set of diverse text prompts. We then use the human-labeled image-text dataset to train a reward function that predicts human feedback

Model-based reinforcement learning (RL) enjoys several benefits, such as\ndata-efficiency and planning, by learning a model of the environment's\ndynamics. However, learning a global model that can generalize across different\ndynamics is a challenging task. To tackle this problem, we decompose the task\nof learning a global dynamics model into two stages: (a) learning a context\nlatent vector that captures the local dynamics, then (b) predicting the next\nstate conditioned on it. In order to en

Ensemble methods are arguably the most trustworthy techniques for boosting the performance of machine learning models. Popular independent ensembles (IE) relying on naive averaging/voting scheme have been of typical choice for most applications involving deep neural networks, but they do not consider advanced collaboration among ensemble models. In this paper, we propose new ensemble methods specialized for deep neural networks, called confident multiple choice learning (CMCL): it is a variant o

Ensemble methods are arguably the most trustworthy techniques for boosting the performance of machine learning models. Popular independent ensembles (IE) relying on naive averaging/voting scheme have been of typical choice for most applications involving deep neural networks, but they do not consider advanced collaboration among ensemble models. In this paper, we propose new ensemble methods specialized for deep neural networks, called confident multiple choice learning (CMCL): it is a variant o

Conveying complex objectives to reinforcement learning (RL) agents can often be difficult, involving meticulous design of reward functions that are sufficiently informative yet easy enough to provide. Human-in-the-loop RL methods allow practitioners to instead interactively teach agents through tailored feedback; however, such approaches have been challenging to scale since human feedback is very expensive. In this work, we aim to make this process more sample- and feedback-efficient. We present

It has been believed that stochastic feedforward neural networks (SFNN) have several advantages beyond deterministic deep neural networks (DNN): they have more expressive power allowing multi-modal mappings and regularize better due to their stochastic nature. However, training SFNN is notoriously harder. In this paper, we aim at developing efficient training methods for large-scale SFNN, in particular using known architectures and pre-trained parameters of DNN. To this end, we propose a new int

In the past years, the centralized management of dense wireless local area networks has been emerged as a powerful paradigm for improving energy efficiency as well as avoiding severe interference. In this paper, we study the joint optimization on power-operation modes in access points (APs), channel selections and user-AP associations for improving energy efficiency and avoiding interference without sacrificing users' demands. To this end, we first formulate it as a mixed-integer programming usi

It has been believed that stochastic feedforward neural networks (SFNNs) have several advantages beyond deterministic deep neural networks (DNNs): they have more expressive power allowing multi-modal mappings and regularize better due to their stochastic nature. However, training large-scale SFNN is notoriously harder. In this paper, we aim at developing efficient training methods for SFNN, in particular using known architectures and pre-trained parameters of DNN. To this end, we propose a new i