Search Results for author:
Found 57 papers, 22 papers with code
Intriguing Properties of Robust Classification
We come to the conclusion that on this datasets, the limitation of current robust models also lies in the generalization, and that they require a lot of data to do well on the test set.
DP-KAN: Differentially Private Kolmogorov-Arnold Networks
We study the Kolmogorov-Arnold Network (KAN), recently proposed as an alternative to the classical Multilayer Perceptron (MLP), in the application for differentially private model training.
Can LLMs Separate Instructions From Data? And What Do We Even Mean By That?
We also present a new dataset, SEP, that allows estimating the measure for real-world models.
More Flexible PAC-Bayesian Meta-Learning by Learning Learning Algorithms
We introduce a new framework for studying meta-learning methods using PAC-Bayesian theory.
1-Lipschitz Layers Compared: Memory Speed and Certifiable Robustness
The robustness of neural networks against input perturbations with bounded magnitude represents a serious concern in the deployment of deep learning models in safety-critical systems.
ELSA: Partial Weight Freezing for Overhead-Free Sparse Network Deployment
We present ELSA, a practical solution for creating deep networks that can easily be deployed at different levels of sparsity.
1-Lipschitz Layers Compared: Memory, Speed, and Certifiable Robustness
The robustness of neural networks against input perturbations with bounded magnitude represents a serious concern in the deployment of deep learning models in safety-critical systems.
Continual Learning: Applications and the Road Forward
Continual learning is a subfield of machine learning, which aims to allow machine learning models to continuously learn on new data, by accumulating knowledge without forgetting what was learned in the past.
1-Lipschitz Neural Networks are more expressive with N-Activations
A crucial property for achieving secure, trustworthy and interpretable deep learning systems is their robustness: small changes to a system's inputs should not result in large changes to its outputs.
PeFLL: Personalized Federated Learning by Learning to Learn
We present PeFLL, a new personalized federated learning algorithm that improves over the state-of-the-art in three aspects: 1) it produces more accurate models, especially in the low-data regime, and not only for clients present during its training phase, but also for any that may emerge in the future; 2) it reduces the amount of on-client computation and client-server communication by providing future clients with ready-to-use personalized models that require no additional finetuning or optimization; 3) it comes with theoretical guarantees that establish generalization from the observed clients to future ones.
Predicting the Geolocation of Tweets Using transformer models on Customized Data
This research is aimed to solve the tweet/user geolocation prediction task and provide a flexible methodology for the geotagging of textual big data.
Cross-client Label Propagation for Transductive and Semi-Supervised Federated Learning
We present Cross-Client Label Propagation(XCLP), a new method for transductive federated learning.
Generalization In Multi-Objective Machine Learning
Modern machine learning tasks often require considering not just one but multiple objectives.
Almost-Orthogonal Layers for Efficient General-Purpose Lipschitz Networks
In this work, we propose a new technique for constructing such Lipschitz networks that has a number of desirable properties: it can be applied to any linear network layer (fully-connected or convolutional), it provides formal guarantees on the Lipschitz constant, it is easy to implement and efficient to run, and it can be combined with any training objective and optimization method.
CrAM: A Compression-Aware Minimizer
In this work we propose a new compression-aware minimizer dubbed CrAM that modifies the optimization step in a principled way, in order to produce models whose local loss behavior is stable under compression operations such as pruning.
Lightweight Conditional Model Extrapolation for Streaming Data under Class-Prior Shift
We introduce LIMES, a new method for learning with non-stationary streaming data, inspired by the recent success of meta-learning.
SSSE: Efficiently Erasing Samples from Trained Machine Learning Models
The availability of large amounts of user-provided data has been key to the success of machine learning for many real-world tasks.
FLEA: Provably Robust Fair Multisource Learning from Unreliable Training Data
In this work we address the problem of fair learning from unreliable training data in the robust multisource setting, where the available training data comes from multiple sources, a fraction of which might not be representative of the true data distribution.
Unsupervised Video Prediction from a Single Frame by Estimating 3D Dynamic Scene Structure
Our goal in this work is to generate realistic videos given just one initial frame as input.
Towards Understanding Knowledge Distillation
Knowledge distillation, i. e., one classifier being trained on the outputs of another classifier, is an empirically very successful technique for knowledge transfer between classifiers.
Fairness-Aware PAC Learning from Corrupted Data
Addressing fairness concerns about machine learning models is a crucial step towards their long-term adoption in real-world automated systems.
Fairness Through Regularization for Learning to Rank
Given the abundance of applications of ranking in recent years, addressing fairness concerns around automated ranking systems becomes necessary for increasing the trust among end-users.
A Flexible Selection Scheme for Minimum-Effort Transfer Learning
Fine-tuning is a popular way of exploiting knowledge contained in a pre-trained convolutional network for a new visual recognition task.
Unsupervised object-centric video generation and decomposition in 3D
A natural approach to generative modeling of videos is to represent them as a composition of moving objects.
Functional vs. parametric equivalence of ReLU networks
We address the following question: How redundant is the parameterisation of ReLU networks?
Localizing Grouped Instances for Efficient Detection in Low-Resource Scenarios
State-of-the-art detection systems are generally evaluated on their ability to exhaustively retrieve objects densely distributed in the image, across a wide variety of appearances and semantic categories.
Leveraging 2D Data to Learn Textured 3D Mesh Generation
Thus, it learns to generate meshes that when rendered, produce images similar to those in its training set.
Object-Centric Image Generation with Factored Depths, Locations, and Appearances
We present a generative model of images that explicitly reasons over the set of objects they show.
On the Sample Complexity of Adversarial Multi-Source PAC Learning
We study the problem of learning from multiple untrusted data sources, a scenario of increasing practical relevance given the recent emergence of crowdsourcing and collaborative learning paradigms.
Back to square one: probabilistic trajectory forecasting without bells and whistles
We introduce a spatio-temporal convolutional neural network model for trajectory forecasting from visual sources.
Detecting Visual Relationships Using Box Attention
We propose a new model for detecting visual relationships, such as "person riding motorcycle" or "bottle on table".
Learning Equations for Extrapolation and Control
We present an approach to identify concise equations from data using a shallow neural network approach.
KS(conf ): A Light-Weight Test if a ConvNet Operates Outside of Its Specifications
Computer vision systems for automatic image categorization have become accurate and reliable enough that they can run continuously for days or even years as components of real-world commercial applications.
Zero-Shot Learning -- A Comprehensive Evaluation of the Good, the Bad and the Ugly
Due to the importance of zero-shot learning, i. e. classifying images where there is a lack of labeled training data, the number of proposed approaches has recently increased steadily.
Probabilistic Image Colorization
We develop a probabilistic technique for colorizing grayscale natural images.
Data-Dependent Stability of Stochastic Gradient Descent
We establish a data-dependent notion of algorithmic stability for Stochastic Gradient Descent (SGD), and employ it to develop novel generalization bounds.
PixelCNN Models with Auxiliary Variables for Natural Image Modeling
We study probabilistic models of natural images and extend the autoregressive family of PixelCNN architectures by incorporating auxiliary variables.
Ranked #17 on
Image Generation
on ImageNet 64x64
(Bits per dim metric)
iCaRL: Incremental Classifier and Representation Learning
A major open problem on the road to artificial intelligence is the development of incrementally learning systems that learn about more and more concepts over time from a stream of data.
Ranked #2 on
Incremental Learning
on ImageNet100 - 10 steps
(# M Params metric)
Extrapolation and learning equations
In classical machine learning, regression is treated as a black box process of identifying a suitable function from a hypothesis set without attempting to gain insight into the mechanism connecting inputs and outputs.
Improving Weakly-Supervised Object Localization By Micro-Annotation
Weakly-supervised object localization methods tend to fail for object classes that consistently co-occur with the same background elements, e. g. trains on tracks.
Seed, Expand and Constrain: Three Principles for Weakly-Supervised Image Segmentation
We introduce a new loss function for the weakly-supervised training of semantic image segmentation models based on three guiding principles: to seed with weak localization cues, to expand objects based on the information about which classes can occur in an image, and to constrain the segmentations to coincide with object boundaries.
Multi-Task Learning with Labeled and Unlabeled Tasks
In contrast to previous work, which required that annotated training data is available for all tasks, we consider a new setting, in which for some tasks, potentially most of them, only unlabeled training data is provided.
Lifelong Learning with Non-i.i.d. Tasks
In the first case we prove a PAC-Bayesian theorem, which can be seen as a direct generalization of the analogous previous result for the i. i. d.
Conditional Risk Minimization for Stochastic Processes
In particular, we aim at learning predictors that minimize the conditional risk for a stochastic process, i. e. the expected loss of the predictor on the next point conditioned on the set of training samples observed so far.
Classifier Adaptation at Prediction Time
Experiments on the ILSVRC2010 and ILSVRC2012 datasets show that adapting object classification systems at prediction time can significantly reduce their error rate, even with no additional human feedback.
Identifying Reliable Annotations for Large Scale Image Segmentation
In this work, we present a Gaussian process (GP) based technique for simultaneously identifying which images of a training set have unreliable annotation and learning a segmentation model in which the negative effect of these images is suppressed.
Curriculum Learning of Multiple Tasks
Sharing information between multiple tasks enables algorithms to achieve good generalization performance even from small amounts of training data.
Learning to Transfer Privileged Information
We interpret these methods as learning easiness and hardness of the objects in the privileged space and then transferring this knowledge to train a better classifier in the original space.
A Multi-Plane Block-Coordinate Frank-Wolfe Algorithm for Training Structural SVMs with a Costly max-Oracle
Structural support vector machines (SSVMs) are amongst the best performing models for structured computer vision tasks, such as semantic image segmentation or human pose estimation.
Mind the Nuisance: Gaussian Process Classification using Privileged Noise
That is, in contrast to the standard GPC setting, the latent function is not just a nuisance but a feature: it becomes a natural measure of confidence about the training data by modulating the slope of the GPC sigmoid likelihood function.
Predicting the Future Behavior of a Time-Varying Probability Distribution
Our main contribution is a method for predicting the next step of the time-varying distribution from a given sequence of sample sets from earlier time steps.
Deep Fisher Kernels - End to End Learning of the Fisher Kernel GMM Parameters
Fisher Kernels and Deep Learning were two developments with significant impact on large-scale object categorization in the last years.
Closed-Form Training of Conditional Random Fields for Large Scale Image Segmentation
It is inspired by existing closed-form expressions for the maximum likelihood parameters of a generative graphical model with tree topology.
A PAC-Bayesian bound for Lifelong Learning
Transfer learning has received a lot of attention in the machine learning community over the last years, and several effective algorithms have been developed.
Attribute-Based Classification for Zero-Shot Visual Object Categorization
To tackle the problem, we introduce attribute-based classification: Objects are identified based on a high-level description that is phrased in terms of semantic attributes, such as the object’s color or shape.
Dynamic Pruning of Factor Graphs for Maximum Marginal Prediction
MMP is typically performed as a two-stage procedure: one estimates each variable's marginal probability and then forms a prediction from the states of maximal probability.
Maximum Margin Multi-Label Structured Prediction
We study multi-label prediction for structured output spaces, a problem that occurs, for example, in object detection in images, secondary structure prediction in computational biology, and graph matching with symmetries.
