论文检索

Theory · Active Learning and Interactive Learning

Luca Franco, Paolo Mandica, Konstantinos Kallidromitis, Devin Guillory, Yu-Teng Li, Trevor Darrell, Fabio Galasso

We introduce a hyperbolic neural network approach to pixel-level active learning for semantic segmentation. Analysis of the data statistics leads to a novel interpretation of the hyperbolic radius as an indicator of data scarcity. In HALO (Hyperbolic Active Learning Optimization), for the first time, we propose the use of epistemic uncertainty as a data acquisition strategy, following the intuition of selecting data points that are the least known. The hyperbolic radius, complemented by the widely-adopted prediction entropy, effectively approximates epistemic uncertainty. We perform extensive experimental analysis based on two established synthetic-to-real benchmarks, i.e. GTAV $\rightarrow$ Cityscapes and SYNTHIA $\rightarrow$ Cityscapes. Additionally, we test HALO on Cityscape $\rightarrow$ ACDC for domain adaptation under adverse weather conditions, and we benchmark both convolutional and attention-based backbones. HALO sets a new state-of-the-art in active learning for semantic segmentation under domain shift and it is the first active learning approach that surpasses the performance of supervised domain adaptation while using only a small portion of labels (i.e., 1%).

Optimization · Non-Convex

Nikita Doikov, Sebastian Stich, Martin Jaggi

The performance of optimization methods is often tied to the spectrum of the objective Hessian. Yet, conventional assumptions, such as smoothness, do often not enable us to make finely-grained convergence statements—particularly not for non-convex problems. Striving for a more intricate characterization of complexity, we introduce a unique concept termed graded non-convexity. This allows to partition the class of non-convex problems into a nested chain of subclasses. Interestingly, many traditional non-convex objectives, including partially convex problems, matrix factorizations, and neural networks, fall within these subclasses. As a second contribution, we propose gradient methods with spectral preconditioning, which employ inexact top eigenvectors of the Hessian to address the ill-conditioning of the problem, contingent on the grade. Our analysis reveals that these new methods provide provably superior convergence rates compared to basic gradient descent on applicable problem classes, particularly when large gaps exist between the top eigenvalues of the Hessian. Our theory is validated by numerical experiments executed on multiple practical machine learning problems.

Lisang Ding, Ziang Chen, Xinshang Wang, Wotao Yin

In this work, we propose a novel optimization model termed ``sum-of-minimum" optimization. This model seeks to minimize the sum or average of $N$ objective functions over $k$ parameters, where each objective takes the minimum value of a predefined sub-function with respect to the $k$ parameters. This universal framework encompasses numerous clustering applications in machine learning and related fields. We develop efficient algorithms for solving sum-of-minimum optimization problems, inspired by a randomized initialization algorithm for the classic $k$-means (Arthur & Vassilvitskii, 2007) and Lloyd's algorithm (Lloyd, 1982). We establish a new tight bound for the generalized initialization algorithm and prove a gradient-descent-like convergence rate for generalized Lloyd's algorithm. The efficiency of our algorithms is numerically examined on multiple tasks, including generalized principal component analysis, mixed linear regression, and small-scale neural network training. Our approach compares favorably to previous ones based on simpler-but-less-precise optimization reformulations.

Optimization · Learning for Optimization

Francesco Demelas, Joseph Roux, Mathieu Lacroix, Axel Parmentier

Lagrangian Relaxation stands among the most efficient approaches for solving Mixed Integer Linear Programs (MILPs) with difficult constraints. Given any duals for these constraints, called Lagrangian Multipliers (LMs), it returns a bound on the optimal value of the MILP, and Lagrangian methods seek the LMs giving the best such bound. But these methods generally rely on iterative algorithms resembling gradient descent to maximize the concave piecewise linear dual function: the computational burden grows quickly with the number of relaxed constraints. We introduce a deep learning approach that bypasses the descent, effectively amortizing per instance optimization. A probabilistic encoder based on a graph neural network computes, given a MILP instance and its Continuous Relaxation (CR) solution, high-dimensional representations of relaxed constraints, which are turned into LMs by a decoder. We train the encoder and the decoder jointly by directly optimizing the bound obtained from the predicted multipliers. Our method is applicable to any problem with a compact MILP formulation, and to any Lagrangian Relaxation providing a tighter bound than CR. Experiments on two widely known problems, Multi-Commodity Network Design and Generalized Assignment, show that our approach closes up to 85% of the gap between the continuous relaxation and the best Lagrangian bound, and provides a high-quality warm-start for descent-based Lagrangian methods.

Deep Learning · Algorithms

Ian Colbert, Alessandro Pappalardo, Jakoba Petri-Koenig, Yaman Umuroglu

Quantization techniques commonly reduce the inference costs of neural networks by restricting the precision of weights and activations. Recent studies show that also reducing the precision of the accumulator can further improve hardware efficiency at the risk of numerical overflow, which introduces arithmetic errors that can degrade model accuracy. To avoid numerical overflow while maintaining accuracy, recent work proposed accumulator-aware quantization (A2Q)—a quantization-aware training method that constrains model weights during training to safely use a target accumulator bit width during inference. Although this shows promise, we demonstrate that A2Q relies on an overly restrictive constraint and a sub-optimal weight initialization strategy that each introduce superfluous quantization error. To address these shortcomings, we introduce: (1) an improved bound that alleviates accumulator constraints without compromising overflow avoidance; and (2) a new strategy for initializing quantized weights from pre-trained floating-point checkpoints. We combine these contributions with weight normalization to introduce A2Q+. We identify and characterize the various tradeoffs that arise as a consequence of accumulator constraints and support our analysis with experiments that show A2Q+ significantly improves these trade-offs when compared to prior methods.

Applications · Physics

Jules Berman, Benjamin Peherstorfer

This work introduces reduced models based on Continuous Low Rank Adaptation (CoLoRA) that pre-train neural networks for a given partial differential equation and then continuously adapt low-rank weights in time to rapidly predict the evolution of solution fields at new physics parameters and new initial conditions. The adaptation can be either purely data-driven or via an equation-driven variational approach that provides Galerkin-optimal approximations. Because CoLoRA approximates solution fields locally in time, the rank of the weights can be kept small, which means that only few training trajectories are required offline so that CoLoRA is well suited for data-scarce regimes. Predictions with CoLoRA are orders of magnitude faster than with classical methods and their accuracy and parameter efficiency is higher compared to other neural network approaches.

Nora Belrose, Quintin Pope, Lucia Quirke, Alex Mallen, Xiaoli Fern

The _distributional simplicity bias_ (DSB) posits that neural networks learn low-order moments of the data distribution first, before moving on to higher-order correlations. In this work, we present compelling new evidence for the DSB by showing that networks automatically learn to perform well on maximum-entropy distributions whose low-order statistics match those of the training set early in training, then lose this ability later. We also extend the DSB to discrete domains by proving an equivalence between token $n$-gram frequencies and the moments of embedding vectors, and by finding empirical evidence for the bias in LLMs. Finally we use optimal transport methods to surgically edit the low-order statistics of one class to match those of another, and show that early-training networks treat the edited samples as if they were drawn from the target class. Code is available at https://github.com/EleutherAI/features-across-time.

Deep Learning · Robustness

Anahita Baninajjar, Ahmed Rezine, Amir Aminifar

Machine learning techniques often lack formal correctness guarantees, evidenced by the widespread adversarial examples that plague most deep-learning applications. This lack of formal guarantees resulted in several research efforts that aim at verifying Deep Neural Networks (DNNs), with a particular focus on safety-critical applications. However, formal verification techniques still face major scalability and precision challenges. The over-approximation introduced during the formal verification process to tackle the scalability challenge often results in inconclusive analysis. To address this challenge, we propose a novel framework to generate Verification-Friendly Neural Networks (VNNs). We present a post-training optimization framework to achieve a balance between preserving prediction performance and verification-friendliness. Our proposed framework results in VNNs that are comparable to the original DNNs in terms of prediction performance, while amenable to formal verification techniques. This essentially enables us to establish robustness for more VNNs than their DNN counterparts, in a time-efficient manner.

Optimization · Large Scale, Parallel and Distributed

Aaron Archer, Matthew Fahrbach, Kuikui Liu, Prakash Prabhu

We optimize pipeline parallelism for deep neural network (DNN) inference by partitioning model graphs into $k$ stages and minimizing the running time of the bottleneck stage, including communication. We give practical and effective algorithms for this NP-hard problem, but our emphasis is on tackling the practitioner's dilemma of deciding when a solution is good enough. To this end, we design novel mixed integer programming (MIP) relaxations for proving lower bounds. Applying these methods to a diverse testbed of 369 production models, for $k \in \\{2, 4, 8, 16, 32, 64\\}$, we empirically show that these lower bounds are strong enough to be useful in practice. Our lower bounds are substantially stronger than standard combinatorial bounds. For example, evaluated via geometric means across a production testbed with $k = 16$ pipeline stages, our MIP formulations raise the lower bound from 0.4598 to 0.9452, expressed as a fraction of the best partition found. In other words, our improved lower bounds close the optimality gap by a factor of 9.855x.

Theory · Optimization

Nico Alvarado, Hans Lobel

During the last few years, the field of dynamical systems has been developing innovative tools to study the asymptotic behavior of different optimizers in the context of neural networks. In this work, we redefine an extensively studied optimizer, employing classical techniques from hyperbolic geometry. This new definition is linked to a non-linear differential equation as a continuous limit. Additionally, by utilizing Lyapunov stability concepts, we analyze the asymptotic behavior of its critical points.

Probabilistic Methods · Bayesian Models and Methods

Mohammad Al-Jarrah, Niyizhen Jin, Bamdad Hosseini, Amirhossein Taghvaei

This paper is concerned with the problem of nonlinear filtering, i.e., computing the conditional distribution of the state of a stochastic dynamical system given a history of noisy partial observations. Conventional sequential importance resampling (SIR) particle filters suffer from fundamental limitations, in scenarios involving degenerate likelihoods or high-dimensional states, due to the weight degeneracy issue. In this paper, we explore an alternative method, which is based on estimating the Brenier optimal transport (OT) map from the current prior distribution of the state to the posterior distribution at the next time step. Unlike SIR particle filters, the OT formulation does not require the analytical form of the likelihood. Moreover, it allows us to harness the approximation power of neural networks to model complex and multi-modal distributions and employ stochastic optimization algorithms to enhance scalability. Extensive numerical experiments are presented that compare the OT method to the SIR particle filter and the ensemble Kalman filter, evaluating the performance in terms of sample efficiency, high-dimensional scalability, and the ability to capture complex and multi-modal distributions.

Theory · Deep Learning

Blake Bordelon, Alexander Atanasov, Cengiz Pehlevan

On a variety of tasks, the performance of neural networks predictably improves with training time, dataset size and model size across many orders of magnitude. This phenomenon is known as a neural scaling law. Of fundamental importance is the compute-optimal scaling law, which reports the performance as a function of units of compute when choosing model sizes optimally. We analyze a random feature model trained with gradient descent as a solvable model of network training and generalization. This reproduces many observations about neural scaling laws. First, our model makes a prediction about why the scaling of performance with training time and with model size have different power law exponents. Consequently, the theory predicts an asymmetric compute-optimal scaling rule where the number of training steps are increased faster than model parameters, consistent with recent empirical observations. Second, it has been observed that early in training, networks converge to their infinite-width dynamics at a rate $1/\text{width}$ but at late time exhibit a rate $\text{width}^{-c}$, where $c$ depends on the structure of the architecture and task. We show that our model exhibits this behavior. Lastly, our theory shows how the gap between training and test loss can gradually build up over time due to repeated reuse of data.

Applications · Computer Vision

Xiaole Tang, Hu Xin, Xiang Gu, Jian Sun

Deep learning-based image restoration methods generally struggle with faithfully preserving the structures of the original image. In this work, we propose a novel Residual-Conditioned Optimal Transport (RCOT) approach, which models image restoration as an optimal transport (OT) problem for both unpaired and paired settings, introducing the transport residual as a unique degradation-specific cue for both the transport cost and the transport map. Specifically, we first formalize a Fourier residual-guided OT objective by incorporating the degradation-specific information of the residual into the transport cost. We further design the transport map as a two-pass RCOT map that comprises a base model and a refinement process, in which the transport residual is computed by the base model in the first pass and then encoded as a degradation-specific embedding to condition the second-pass restoration. By duality, the RCOT problem is transformed into a minimax optimization problem, which can be solved by adversarially training neural networks. Extensive experiments on multiple restoration tasks show that RCOT achieves competitive performance in terms of both distortion measures and perceptual quality, restoring images with more faithful structures as compared with state-of-the-art methods.

Miscellaneous Aspects of Machine Learning · Kernel methods

Eiki Shimizu, Kenji Fukumizu, Dino Sejdinovic

Kernel conditional mean embeddings (CMEs) offer a powerful framework for representing conditional distributions, but they often face scalability and expressiveness challenges. In this work, we propose a new method that effectively combines the strengths of deep learning with CMEs in order to address these challenges. Specifically, our approach leverages the end-to-end neural network (NN) optimization framework using a kernel-based objective. This design circumvents the computationally expensive Gram matrix inversion required by current CME methods. To further enhance performance, we provide efficient strategies to optimize the remaining kernel hyperparameters. In conditional density estimation tasks, our NN-CME hybrid achieves competitive performance and often surpasses existing deep learning-based methods. Lastly, we showcase its remarkable versatility by seamlessly integrating it into reinforcement learning (RL) contexts. Building on Q-learning, our approach naturally leads to a new variant of distributional RL methods, which demonstrates consistent effectiveness across different environments.

Reinforcement Learning · Deep RL

Mudit Gaur, Amrit Singh Bedi, Di Wang, Vaneet Aggarwal

The current state-of-the-art theoretical analysis of Actor-Critic (AC) algorithms significantly lags in addressing the practical aspects of AC implementations. This crucial gap needs bridging to bring the analysis in line with practical implementations of AC. To address this, we advocate for considering the MMCLG criteria: **M**ulti-layer neural network parametrization for actor/critic, **M**arkovian sampling, **C**ontinuous state-action spaces, the performance of the **L**ast iterate, and **G**lobal optimality. These aspects are practically significant and have been largely overlooked in existing theoretical analyses of AC algorithms. In this work, we address these gaps by providing the first comprehensive theoretical analysis of AC algorithms that encompasses all five crucial practical aspects (covers MMCLG criteria). We establish global convergence sample complexity bounds of $\tilde{\mathcal{O}}\left( \epsilon^{-3} \right)$. We achieve this result through our novel use of the weak gradient domination property of MDP's and our unique analysis of the error in critic estimation.

Deep Learning · Theory

Xuran Meng, Difan Zou, Yuan Cao

Modern deep learning models are usually highly over-parameterized so that they can overfit the training data. Surprisingly, such overfitting neural networks can usually still achieve high prediction accuracy. To study this ``benign overfitting'' phenomenon, a line of recent works has theoretically studied the learning of linear models and two-layer neural networks. However, most of these analyses are still limited to the very simple learning problems where the Bayes-optimal classifier is linear. In this work, we investigate a class of XOR-type classification tasks with label-flipping noises. We show that, under a certain condition on the sample complexity and signal-to-noise ratio, an over-parameterized ReLU CNN trained by gradient descent can achieve near Bayes-optimal accuracy. Moreover, we also establish a matching lower bound result showing that when the previous condition is not satisfied, the prediction accuracy of the obtained CNN is an absolute constant away from the Bayes-optimal rate. Our result demonstrates that CNNs have a remarkable capacity to efficiently learn XOR problems, even in the presence of highly correlated features.

Deep Learning

Pratik Rathore, Weimu Lei, Zachary Frangella, Lu Lu, Madeleine Udell

This paper explores challenges in training Physics-Informed Neural Networks (PINNs), emphasizing the role of the loss landscape in the training process. We examine difficulties in minimizing the PINN loss function, particularly due to ill-conditioning caused by differential operators in the residual term. We compare gradient-based optimizers Adam, L-BFGS, and their combination Adam+L-BFGS, showing the superiority of Adam+L-BFGS, and introduce a novel second-order optimizer, NysNewton-CG (NNCG), which significantly improves PINN performance. Theoretically, our work elucidates the connection between ill-conditioned differential operators and ill-conditioning in the PINN loss and shows the benefits of combining first- and second-order optimization methods. Our work presents valuable insights and more powerful optimization strategies for training PINNs, which could improve the utility of PINNs for solving difficult partial differential equations.

Applications · Physics

Woojin Cho, Minju Jo, Haksoo Lim, Kookjin Lee, Dongeun Lee, Sanghyun Hong, Noseong Park

Complex physical systems are often described by partial differential equations (PDEs) that depend on parameters such as the Raynolds number in fluid mechanics. In applications such as design optimization or uncertainty quantification, solutions of those PDEs need to be evaluated at numerous points in the parameter space. While physics-informed neural networks (PINNs) have emerged as a new strong competitor as a surrogate, their usage in this scenario remains underexplored due to the inherent need for repetitive and time-consuming training. In this paper, we address this problem by proposing a novel extension, parameterized physics-informed neural networks (P$^2$INNs). P$^2$INNs enable modeling the solutions of parameterized PDEs via explicitly encoding a latent representation of PDE parameters. With the extensive empirical evaluation, we demonstrate that P$^2$INNs outperform the baselines both in accuracy and parameter efficiency on benchmark 1D and 2D parameterized PDEs and are also effective in overcoming the known “failure modes”.

Deep Learning · Robustness

Yunjuan Wang, Kaibo Zhang, Raman Arora

Benign overfitting is the phenomenon wherein none of the predictors in the hypothesis class can achieve perfect accuracy (i.e., non-realizable or noisy setting), but a model that interpolates the training data still achieves good generalization. A series of recent works aim to understand this phenomenon for regression and classification tasks using linear predictors as well as two-layer neural networks. In this paper, we study such a benign overfitting phenomenon in an adversarial setting. We show that under a distributional assumption, interpolating neural networks found using adversarial training generalize well despite inference-time attacks. Specifically, we provide convergence and generalization guarantees for adversarial training of two-layer networks (with smooth as well as non-smooth activation functions) showing that under moderate $\ell_2$ norm perturbation budget, the trained model has near-zero robust training loss and near-optimal robust generalization error. We support our theoretical findings with an empirical study on synthetic and real-world data.

Zhengyang Hu, Song Kang, Qunsong Zeng, Kaibin Huang, Yanchao Yang

Estimating mutual correlations between random variables or data streams is essential for intelligent behavior and decision-making. As a fundamental quantity for measuring statistical relationships, mutual information has been extensively studied and utilized for its generality and equitability. However, existing methods often lack the efficiency needed for real-time applications, such as test-time optimization of a neural network, or the differentiability required for end-to-end learning, like histograms. We introduce a neural network called InfoNet, which directly outputs mutual information estimations of data streams by leveraging the attention mechanism and the computational efficiency of deep learning infrastructures. By maximizing a dual formulation of mutual information through large-scale simulated training, our approach circumvents time-consuming test-time optimization and offers generalization ability. We evaluate the effectiveness and generalization of our proposed mutual information estimation scheme on various families of distributions and applications. Our results demonstrate that InfoNet and its training process provide a graceful efficiency-accuracy trade-off and order-preserving properties. We will make the code and models available as a comprehensive toolbox to facilitate studies in different fields requiring real-time mutual information estimation.