论文检索

Probabilistic Methods · Variational Inference

Zhanfeng Mo, Haosen Shi, Sinno Jialin Pan

Neural pruning aims to compress and accelerate deep neural networks by identifying the optimal subnetwork within a specified sparsity budget. In this work, we study how to gradually sparsify the unpruned dense model to the target sparsity level with minimal performance drop. Specifically, we analyze the evolution of the population of optimal subnetworks under continuous sparsity increments from a thermodynamic perspective. We first reformulate neural pruning as an expected loss minimization problem over the mask distributions. Then, we establish an effective approximation for the sparsity evolution of the optimal mask distribution, termed the **S**parsity Evolutionary **F**okker-**P**lanck-**K**olmogorov Equation (**SFPK**), which provides closed-form, mathematically tractable guidance on distributional transitions for minimizing the expected loss under an infinitesimal sparsity increment. On top of that, we propose SFPK-pruner, a particle simulation-based probabilistic pruning method, to sample performant masks with desired sparsity from the destination distribution of SFPK. In theory, we establish the convergence guarantee for the proposed SFPK-pruner. Our SFPK-pruner exhibits competitive performance in various pruning scenarios. The code is available on https://github.com/mzf666/SFPK-main.

Reinforcement Learning · Everything Else

Yannick Metz, Andras Geiszl, Raphaël Baur, Mennatallah El-Assady

Learning rewards from preference feedback has become an important tool in the alignment of agentic models. Preference-based feedback, often implemented as a binary comparison between multiple completions, is an established method to acquire large-scale human feedback. However, human feedback in other contexts is often much more diverse. Such diverse feedback can better support the goals of a human annotator, and the simultaneous use of multiple sources might be mutually informative for the learning process or carry type-dependent biases for the reward learning process.Despite these potential benefits, learning from different feedback types has yet to be explored extensively.In this paper, we bridge this gap by enabling experimentation and evaluating multi-type feedback in a wide set of environments. We present a process to generate high-quality simulated feedback of six different types. Then, we implement reward models and downstream RL training for all six feedback types.Based on the simulated feedback, we investigate the use of types of feedback across ten RL environments and compare them to pure preference-based baselines. We show empirically that diverse types of feedback can be utilized and lead to strong reward modeling performance. This work is the first strong indicator of the potential of multi-type feedback for RLHF.

Optimization · Everything Else

Zhanfeng Mo, Long-Kai Huang, Sinno Jialin Pan

Pretraining large language models often requires significant computational resources and memory due to their vast parameter amount. An effective approach to enhance parameter efficiency in both training and inference is to parameterize each full-size weight as the product of two trainable low-rank factors. While low-rank fine-tuning has achieved great success, low-rank pretraining remains challenging as it requires learning extensive knowledge from scratch under the restrictive low-rank parameterization. During standard low-rank pretraining, separately optimizing the low-rank factors introduces redundant information from the full gradient, which hinders the learning process. To achieve efficient yet effective low-rank pretraining, we propose a **Lo**w-rank **R**iemannian **O**ptimizer (**LORO**). At each LORO update step, the low-rank factor pairs are jointly updated to ensure their full-size product moves along the steepest descent direction on the low-rank manifold, without the need to compute any memory-intensive full-size matrices or gradients. Hence, our LORO finds low-rank models that achieve high performance comparable to full-size pretrained models, while significantly reducing memory usage and accelerating both training and inference. A LLaMA 1B model pretrained with LORO achieves a perplexity score of 2\% better than the full-size baseline, with a 54\% reduction in model memory, a $\times1.8$ speedup in training, and a $\times2.2$ speedup in inference. The code is available on https://github.com/mzf666/LORO-main.

Theory · Learning Theory

Florian Eddie Dorner, Vivian Nastl, Moritz Hardt

High quality annotations are increasingly a bottleneck in the explosively growing machine learning ecosystem. Scalable evaluation methods that avoid costly annotation have therefore become an important research ambition. Many hope to use strong existing models in lieu of costly labels to provide cheap model evaluations. Unfortunately, this method of using models as judges introduces biases, such as self-preferencing, that can distort model comparisons. An emerging family of debiasing tools promises to fix these issues by using a few high quality labels to debias a large number of model judgments. In this paper, we study how far such debiasing methods, in principle, can go. Our main result shows that when the judge is no more accurate than the evaluated model, no debiasing method can decrease the required amount of ground truth labels by more than half. Our result speaks to the severe limitations of the LLM-as-a-judge paradigm at the evaluation frontier where the goal is to assess newly released models that are possibly better than the judge. Through an empirical evaluation, we demonstrate that the sample size savings achievable in practice are even more modest than what our theoretical limit suggests. Along the way, our work provides new observations about debiasing methods for model evaluation, and points out promising avenues for future work.

Miscellaneous Aspects of Machine Learning · Transfer, Multitask and Meta-learning

Zhaochong An, Guolei Sun, Yun Liu, Runjia Li, Min Wu, Ming-Ming Cheng, Ender Konukoglu, Serge Belongie

Few-shot 3D point cloud segmentation (FS-PCS) aims at generalizing models to segment novel categories with minimal annotated support samples. While existing FS-PCS methods have shown promise, they primarily focus on unimodal point cloud inputs, overlooking the potential benefits of leveraging multimodal information. In this paper, we address this gap by introducing a multimodal FS-PCS setup, utilizing textual labels and the potentially available 2D image modality. Under this easy-to-achieve setup, we present the MultiModal Few-Shot SegNet (MM-FSS), a model effectively harnessing complementary information from multiple modalities. MM-FSS employs a shared backbone with two heads to extract intermodal and unimodal visual features, and a pretrained text encoder to generate text embeddings. To fully exploit the multimodal information, we propose a Multimodal Correlation Fusion (MCF) module to generate multimodal correlations, and a Multimodal Semantic Fusion (MSF) module to refine the correlations using text-aware semantic guidance. Additionally, we propose a simple yet effective Test-time Adaptive Cross-modal Calibration (TACC) technique to mitigate training bias, further improving generalization. Experimental results on S3DIS and ScanNet datasets demonstrate significant performance improvements achieved by our method. The efficacy of our approach indicates the benefits of leveraging commonly-ignored free modalities for FS-PCS, providing valuable insights for future research. The code is available at github.com/ZhaochongAn/Multimodality-3D-Few-Shot.

Deep Learning · Algorithms

Han-Jia Ye, Huai-Hong Yin, De-Chuan Zhan, Wei-Lun Chao

The widespread enthusiasm for deep learning has recently expanded into the domain of tabular data. Recognizing that the advancement in deep tabular methods is often inspired by classical methods, e.g., integration of nearest neighbors into neural networks, we investigate whether these classical methods can be revitalized with modern techniques.We revisit a differentiable version of $K$-nearest neighbors (KNN) --- Neighbourhood Components Analysis (NCA) --- originally designed to learn a linear projection to capture semantic similarities between instances, and seek to gradually add modern deep learning techniques on top. Surprisingly, our implementation of NCA using SGD and without dimensionality reduction already achieves decent performance on tabular data, in contrast to the results of using existing toolboxes like scikit-learn. Further equipping NCA with deep representations and additional training stochasticity significantly enhances its capability, being on par with the leading tree-based method CatBoost and outperforming existing deep tabular models in both classification and regression tasks on 300 datasets. We conclude our paper by analyzing the factors behind these improvements, including loss functions, prediction strategies, and deep architectures.The code is available at https://github.com/LAMDA-Tabular/TALENT.

Theory · Reinforcement Learning and Planning

Roman Belaire, Arunesh Sinha, Pradeep Varakantham

Deep Reinforcement Learning (DRL) policies are highly susceptible to adversarial noise in observations, which poses significant risks in safety-critical scenarios. The challenge inherent to adversarial perturbations is that by altering the information observed by the agent, the state becomes only partially observable. Existing approaches address this by either enforcing consistent actions across nearby states or maximizing the worst-case value within adversarially perturbed observations. However, the former suffers from performance degradation when attacks succeed, while the latter tends to be overly conservative, leading to suboptimal performance in benign settings. We hypothesize that these limitations stem from their failing to account for partial observability directly. To this end, we introduce a novel objective called Adversarial Counterfactual Error (ACoE), defined on the beliefs about the true state and balancing value optimization with robustness. To make ACoE scalable in model-free settings, we propose the theoretically-grounded surrogate objective Cumulative-ACoE (C-ACoE). Our empirical evaluations on standard benchmarks (MuJoCo, Atari, and Highway) demonstrate that our method significantly outperforms current state-of-the-art approaches for addressing adversarial RL challenges, offering a promising direction for improving robustness in DRL under adversarial conditions. Our code is available at https://github.com/romanbelaire/acoe-robust-rl.

Optimization · Non-Convex

Zeman Li, Xinwei Zhang, Peilin Zhong, Yuan Deng, Meisam Razaviyayn, Vahab Mirrokni

Fine-tuning language models (LMs) with the standard Adam optimizer often demands excessive memory, limiting accessibility. The ``in-place'' version of Stochastic Gradient Descent (IP-SGD) and Memory-Efficient Zeroth-order Optimizer (MeZO) have been proposed as solutions to improve memory efficiency. However, IP-SGD still requires a decent amount of memory, and MeZO suffers from slow convergence and degraded final performance due to its zeroth-order nature. This paper introduces Addax, a novel method that improves both memory efficiency and algorithm performance of IP-SGD by integrating it with MeZO. Specifically, Addax computes the zeroth-order or first-order gradient of the data points in the minibatch based on their memory consumption and combines zeroth- and first-order gradient estimates to obtain the updated direction in each step.By computing the zeroth-order order gradient of data points that require more memory and the first-order gradient of the ones that require less memory, Addax overcomes the slow convergence of MeZO and excessive memory requirement of IP-SGD. Additionally, the zeroth-order gradient acts as a regularizer for the first-order gradient, further enhancing the model's final performance.Theoretically, we establish the convergence of Addax under mild assumptions, demonstrating faster convergence and less restrictive hyper-parameter choices than MeZO. Our extensive experiments with diverse LMs and tasks show that Addax consistently outperforms MeZO in terms of accuracy and convergence speed, while having a comparable memory footprint. In particular, our experiments using one A100 GPU on OPT-13B model reveal that, on average, Addax outperforms MeZO in terms of accuracy/F1 score by 14%, and runs $15\times$ faster, while having a comparable memory footprint to MeZO. In our experiments on the larger OPT-30B model, on average, Addax outperforms MeZO in terms of accuracy/F1 score by >16% and runs $30\times$ faster on a single H100 GPU. Moreover, Addax surpasses the performance of standard fine-tuning approaches, such as IP-SGD and Adam, in most tasks in terms of Accuracy/F1 score with significantly less memory requirement.

Social Aspects · Privacy-preserving Statistics and Machine Learning

Xinwei Zhang, Zhiqi Bu, Borja Balle, Mingyi Hong, Meisam Razaviyayn, Vahab Mirrokni

Differential privacy (DP) offers a robust framework for safeguarding individual data privacy. To utilize DP in training modern machine learning models, differentially private optimizers have been widely used in recent years. A popular approach to privatize an optimizer is to clip the individual gradients and add sufficiently large noise to the clipped gradient. This approach led to the development of DP optimizers that have comparable performance with their non-private counterparts in fine-tuning tasks or in tasks with a small number of training parameters. However, a significant performance drop is observed when these optimizers are applied to large-scale training. This degradation stems from the substantial noise injection required to maintain DP, which disrupts the optimizer's dynamics.This paper introduces DiSK, a novel framework designed to significantly enhance the performance of DP optimizers. DiSK employs Kalman filtering, a technique drawn from control and signal processing, to effectively denoise privatized gradients and generate progressively refined gradient estimations. To ensure practicality for large-scale training, we simplify the Kalman filtering process, minimizing its memory and computational demands.We establish theoretical privacy-utility trade-off guarantees for DiSK, and demonstrate provable improvements over standard DP optimizers like DPSGD in terms of iteration complexity upper-bound.Extensive experiments across diverse tasks, including vision tasks such as CIFAR-100 and ImageNet-1k and language fine-tuning tasks such as GLUE, E2E, and DART, validate the effectiveness of DiSK. The results showcase its ability to significantly improve the performance of DP optimizers, surpassing state-of-the-art results under the same privacy constraints on several benchmarks.

Miscellaneous Aspects of Machine Learning · Transfer, Multitask and Meta-learning

Vivek Farias, Adam Jozefiak

Plasticity Loss is an increasingly important phenomenon that refers to the empirical observation that as a neural network is continually trained on a sequence of changing tasks, its ability to adapt to a new task diminishes over time. We introduce Self-Normalized Resets (SNR), a simple adaptive algorithm that mitigates plasticity loss by resetting a neuron’s weights when evidence suggests its firing rate has effectively dropped to zero. Across a battery of continual learning problems and network architectures, we demonstrate that SNR consistently attains superior performance compared to its competitor algorithms. We also demonstrate that SNR is robust to its sole hyperparameter, its rejection percentile threshold, while competitor algorithms show significant sensitivity. SNR’s threshold-based reset mechanism is motivated by a simple hypothesis test we derive. Seen through the lens of this hypothesis test, competing reset proposals yield suboptimal error rates in correctly detecting inactive neurons, potentially explaining our experimental observations. We also conduct a theoretical investigation of the optimization landscape for the problem of learning a single ReLU. We show that even when initialized adversarially, an idealized version of SNR learns the target ReLU, while regularization based approaches can fail to learn.

Deep Learning · Large Language Models

Gabriel Wu, Jacob Hilton

We consider the problem of *low probability estimation*: given a machine learning model and a formally-specified input distribution, how can we estimate the probability of a binary property of the model's output, even when that probability is too small to estimate by random sampling? This problem is motivated by the need to improve worst-case performance, which distribution shift can make much more likely. We study low probability estimation in the context of argmax sampling from small transformer language models. We compare two types of methods: importance sampling, which involves searching for inputs giving rise to the rare output, and activation extrapolation, which involves extrapolating a probability distribution fit to the model's logits. We find that importance sampling outperforms activation extrapolation, but both outperform naive sampling. Finally, we explain how minimizing the probability estimate of an undesirable behavior generalizes adversarial training, and argue that new methods for low probability estimation are needed to provide stronger guarantees about worst-case performance.

Reinforcement Learning · Everything Else

Sheng Xu, Bo Yue, Hongyuan Zha, Guiliang Liu

Designing reward functions in Reinforcement Learning (RL) often demands significant task-specific expertise. Offline Preference-based Reinforcement Learning (PbRL) provides an effective alternative to address the complexity of reward design by learning policies from offline datasets that contain human preferences between trajectory pairs. Existing offline PbRL studies typically model a reward function by maximizing its likelihood of generating the observed human preferences. However, due to the varying number of samples within the limited dataset, less frequently compared trajectories exhibit greater uncertainty, which potentially leads to unreliable behaviors during reward and policy updates. To solve this issue, in this work, we introduce Uncertainty-Aware PbRL (UA-PbRL) to learn a distributional reward model and a risk-sensitive policy from an offline preference dataset. Our approach employs a Maximum A Posteriori (MAP) objective to update trajectory rewards and incorporates an informative prior to account for the uncertainties. Building upon this reward update, we propose a generative reward model to capture the reward distribution, utilizing the offline distributional Bellman operator and the Conditional Value-at-Risk (CVaR) metric to train a risk-sensitive policy. Experimental results demonstrate that UA-PbRL effectively identifies and avoids states with high uncertainty, facilitating risk-averse behaviors across various tasks, including robot control and language model alignment. The code is available at https://github.com/Jasonxu1225/UA-PbRL.

Jonathan Frankle, Jose Javier Gonzalez Ortiz, Cody Blakeney, Mansheej Paul, Philip Greengard, Dan Biderman, Jacob Portes, Connor Jennings, Daniel King, Sam Havens 等

Low-Rank Adaptation (LoRA) is a widely-used parameter-efficient finetuning method for large language models. LoRA saves memory by training only low rank perturbations to selected weight matrices. In this work, we compare the performance of LoRA and full finetuning on two target domains, programming and mathematics. We consider both the instruction finetuning ($\approx$100K prompt-response pairs) and continued pretraining ($\approx$20B unstructured tokens) data regimes. Our results show that, in the standard low-rank settings, LoRA substantially underperforms full finetuning. Nevertheless, LoRA better maintains the base model's performance on tasks outside the target domain. We show that LoRA mitigates forgetting more than common regularization techniques such as weight decay and dropout; it also helps maintain more diverse generations. Finally, we show that full finetuning learns perturbations with a rank that is 10-100$\times$ greater than typical LoRA configurations, possibly explaining some of the reported gaps. We conclude by proposing best practices for finetuning with LoRA.

Vitalis Vosylius, Edward Johns

Following the impressive capabilities of in-context learning with large transformers, In-Context Imitation Learning (ICIL) is a promising opportunity for robotics. We introduce Instant Policy, which learns new tasks instantly from just one or two demonstrations, achieving ICIL through two key components. First, we introduce inductive biases through a graph representation and model ICIL as a graph generation problem using a learned diffusion process, enabling structured reasoning over demonstrations, observations, and actions. Second, we show that such a model can be trained using pseudo-demonstrations – arbitrary trajectories generated in simulation – as a virtually infinite pool of training data. Our experiments, in both simulation and reality, show that Instant Policy enables rapid learning of various everyday robot tasks. We also show how it can serve as a foundation for cross-embodiment and zero-shot transfer to language-defined tasks.

Miscellaneous Aspects of Machine Learning · Representation Learning

Md Ashiqur Rahman, Raymond A. Yeh

Downsampling layers are crucial building blocks in CNN architectures, which help to increase the receptive field for learning high-level features and reduce the amount of memory/computation in the model. In this work, we study the generalization of the uniform downsampling layer for group equivariant architectures, e.g., $G$-CNNs. That is, we aim to downsample signals (feature maps) on general finite groups *with* anti-aliasing. This involves the following: **(a)** Given a finite group and a downsampling rate, we present an algorithm to form a suitable choice of subgroup. **(b)** Given a group and a subgroup, we study the notion of bandlimited-ness and propose how to perform anti-aliasing. Notably, our method generalizes the notion of downsampling based on classical sampling theory. When the signal is on a cyclic group, i.e., periodic, our method recovers the standard downsampling of an ideal low-pass filter followed by a subsampling operation. Finally, we conducted experiments on image classification tasks demonstrating that the proposed downsampling operation improves accuracy, better preserves equivariance, and reduces model size when incorporated into $G$-equivariant networks

Applications · Robotics

Vitalis Vosylius, Edward Johns

Following the impressive capabilities of in-context learning with large transformers, In-Context Imitation Learning (ICIL) is a promising opportunity for robotics. We introduce Instant Policy, which learns new tasks instantly from just one or two demonstrations, achieving ICIL through two key components. First, we introduce inductive biases through a graph representation and model ICIL as a graph generation problem using a learned diffusion process, enabling structured reasoning over demonstrations, observations, and actions. Second, we show that such a model can be trained using pseudo-demonstrations – arbitrary trajectories generated in simulation – as a virtually infinite pool of training data. Our experiments, in both simulation and reality, show that Instant Policy enables rapid learning of various everyday robot tasks. We also show how it can serve as a foundation for cross-embodiment and zero-shot transfer to language-defined tasks.

Applications · Time Series

Wei Wu, Can Liao, Zizhen Deng, Zhengrui Guo, Jinzhuo Wang

The Platonic Representation Hypothesis posits that behind different modalities of data (what we sense or detect), there exists a universal, modality-independent representation of reality. Inspired by this, we treat each neuron as a system, where we can detect the neuron’s multi-segment activity data under different peripheral conditions. We believe that, similar to the Platonic idea, there exists a time-invariant representation behind the different segments of the same neuron, which reflects the intrinsic properties of the neuron’s system. Intrinsic properties include the molecular profiles, brain regions and morphological structure, etc. The optimization objective for obtaining the intrinsic representation of neurons should satisfy two criteria: (I) segments from the same neuron should have a higher similarity than segments from different neurons; (II) the representations should generalize well to out-of-domain data. To achieve this, we employ contrastive learning, treating different segments from the same neuron as positive pairs and segments from different neurons as negative pairs. During the implementation, we chose the VICReg, which uses only positive pairs for optimization but indirectly separates dissimilar samples via regularization terms. To validate the efficacy of our method, we first applied it to simulated neuron population dynamics data generated using the Izhikevich model. We successfully confirmed that our approach captures the type of each neuron as defined by preset hyperparameters. We then applied our method to two real-world neuron dynamics datasets, including spatial transcriptomics-derived neuron type annotations and the brain regions where each neuron is located. The learned representations from our model not only predict neuron type and location but also show robustness when tested on out-of-domain data (unseen animals). This demonstrates the potential of our approach in advancing the understanding of neuronal systems and offers valuable insights for future neuroscience research.

Deep Learning · Generative Models and Autoencoders

Minh-Quan Le, Gaurav Mittal, Tianjian Meng, A S M Iftekhar, Vishwas Suryanarayanan, Barun Patra, Dimitris Samaras, Mei Chen

While diffusion models are powerful in generating high-quality, diverse synthetic data for object-centric tasks, existing methods struggle with scene-aware tasks such as Visual Question Answering (VQA) and Human-Object Interaction (HOI) Reasoning, where it is critical to preserve scene attributes in generated images consistent with a multimodal context, i.e. a reference image with accompanying text guidance query. To address this, we introduce **Hummingbird**, the first diffusion-based image generator which, given a multimodal context, generates highly diverse images w.r.t. the reference image while ensuring high fidelity by accurately preserving scene attributes, such as object interactions and spatial relationships from the text guidance. Hummingbird employs a novel Multimodal Context Evaluator that simultaneously optimizes our formulated Global Semantic and Fine-grained Consistency Rewards to ensure generated images preserve the scene attributes of reference images in relation to the text guidance while maintaining diversity. As the first model to address the task of maintaining both diversity and fidelity given a multimodal context, we introduce a new benchmark formulation incorporating MME Perception and Bongard HOI datasets. Benchmark experiments show Hummingbird outperforms all existing methods by achieving superior fidelity while maintaining diversity, validating Hummingbird's potential as a robust multimodal context-aligned image generator in complex visual tasks. Project page: https://roar-ai.github.io/hummingbird

Miscellaneous Aspects of Machine Learning · Unsupervised and Semi-supervised Learning

Vishwajeet Agrawal, Rattana Pukdee, Nina Balcan, Pradeep K Ravikumar

We study programmatic weak supervision, where in contrast to labeled data, we have access to \emph{weak labelers}, each of which either abstains or provides noisy labels corresponding to any input. Most previous approaches typically employ latent generative models that model the joint distribution of the weak labels and the latent ``true'' label. The caveats are that this relies on assumptions that may not always hold in practice such as conditional independence assumptions over the joint distribution of the weak labelers and the latent true label, and more general implicit inductive biases in the latent generative models. In this work, we consider a more explicit form of side-information that can be leveraged to denoise the weak labeler, namely the bounds on the average error of the weak labelers. We then propose a novel but natural weak supervision objective that minimizes a regularization functional subject to satisfying these bounds. This turns out to be a difficult constrained optimization problem due to discontinuous accuracy bound constraints. We provide a continuous optimization formulation for this objective through an alternating minimization algorithm that iteratively computes soft pseudo labels on the unlabeled data satisfying the constraints while being close to the model, and then updates the model on these labels until all the constraints are satisfied. We follow this with a theoretical analysis of this approach and provide insights into its denoising effects in training discriminative models given multiple weak labelers. Finally, we demonstrate the superior performance and robustness of our method on a popular weak supervision benchmark.

Applications · Everything Else

Gavin (Zhen) Guo, Adriana Meza Soria, Wei Sun, Yikang Shen, Rameswar Panda

We introduce API Pack, a massive multi-programming language dataset containing over one million instruction-API calls for improving the API call generation capabilities of large language models. Our evaluation highlights three key findings: First, fine-tuning on API Pack enables open-source models to outperform GPT-3.5 and GPT-4 in generating code for entirely new API calls. We show this by fine-tuning CodeLlama-13B on 20,000 Python instances from API Pack. Second, fine-tuning on a large dataset in one language, combined with smaller datasets from others, improves API generation accuracy across multiple languages. Third, we confirm the benefits of larger datasets for API generalization, as increasing fine-tuning data to one million instances enhances generalization to new APIs. To support further research, we open-source the API Pack dataset, trained model, and code at https://github.com/zguo0525/API-Pack.