Comment on Stochastic Polyak Step-Size: Performance of ALI-G

• URL: http://arxiv.org/abs/2105.10011v1
• Date: Thu, 20 May 2021 19:57:34 GMT
• Title: Comment on Stochastic Polyak Step-Size: Performance of ALI-G
• Abstract summary: ALI-G and SPS are both adaptations of the Polyak step-size to optimize machine learning models. We show that when training a ResNet-34 on CIFAR-10 and CIFAR-100, the performance of ALI-G can reach respectively 93.5% (+6%) and 76% (+8%) with a very small amount of tuning.
• Score: 104.83776736573009
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: This is a short note on the performance of the ALI-G algorithm (Berrada et al., 2020) as reported in (Loizou et al., 2021). ALI-G (Berrada et al., 2020) and SPS (Loizou et al., 2021) are both adaptations of the Polyak step-size to optimize machine learning models that can interpolate the training data. The main algorithmic differences are that (1) SPS employs a multiplicative constant in the denominator of the learning-rate while ALI-G uses an additive constant, and (2) SPS uses an iteration-dependent maximal learning-rate while ALI-G uses a constant one. There are also differences in the analysis provided by the two works, with less restrictive assumptions proposed in (Loizou et al., 2021). In their experiments, (Loizou et al., 2021) did not use momentum for ALI-G (which is a standard part of the algorithm) or standard hyper-parameter tuning (for e.g. learning-rate and regularization). Hence this note as a reference for the improved performance that ALI-G can obtain with well-chosen hyper-parameters. In particular, we show that when training a ResNet-34 on CIFAR-10 and CIFAR-100, the performance of ALI-G can reach respectively 93.5% (+6%) and 76% (+8%) with a very small amount of tuning. Thus ALI-G remains a very competitive method for training interpolating neural networks.

Related papers

• WarpSAC: Towards the Pinnacle of Scalable Off-policy RL by Rethinking Exploration and Exploitation [67.83495924117089]
  Massively parallel simulation changes the data regime in which off-policy reinforcement learning is trained.<n>We show that these stabilizers are data-regime-dependent.<n>We propose WarpSAC, a regime-aware family of off-policy RL algorithms.
  arXiv  Detail & Related papers  (2026-08-25T12:24:15Z)
• ISO: An RLVR-Native Optimization Stack [50.40395312897848]
  We operationalize spectral inheritance as Isospectral Optimization (ISO)<n>Offline, ISO-Merger combines the frame changes of shared-base specialists into a single fixed-spectrum model.<n>Online, ISO-Merger applies a chosen base, including AdamW and Muon, to the frame variables while keeping the base spectra fixed.
  arXiv  Detail & Related papers  (2026-07-21T17:51:36Z)
• Supervised Fine-Tuning vs. In-Context Learning: An Equilibrium Analysis of LLM Personalization under Congestion [52.722575491987904]
  We show that ICL and SFT dominate in different regimes, determined by an interplay between pretraining coverage and data signal-to-noise ratios.<n>We prove that offering both personalization methods never hurts the platform's maximal profits, despite potentially increasing computational load.
  arXiv  Detail & Related papers  (2026-07-15T21:17:42Z)
• Learn Where Outcomes Diverge: Efficient VLA RL via Probabilistic Chunk Masking [5.238545250784642]
  This paper presents Probabilistic Chunk Masking (PCM), a drop-in modification to GRPO that allocates gradient to a small, probabilistically selected subset of chunks per trajectory.<n>On three LIBERO benchmarks, PCM matches the final success rate of standard GRPO while achieving 2.38 times wall-clock speedup, 4.8 times faster gradient updates, and 60% lower peak activation memory.
  arXiv  Detail & Related papers  (2026-05-15T16:33:59Z)
• Why Agent Caching Fails and How to Fix It: Structured Intent Canonicalization with Few-Shot Learning [0.0]
  Cache effectiveness requires key consistency and precision, not classification accuracy.<n>We introduce W5H2, a structured intent decomposition framework.<n>On NyayaBench v2 (20 classes), SetFit achieves 55.3%, with cross-lingual transfer across 30 languages.
  arXiv  Detail & Related papers  (2026-02-21T18:25:18Z)
• From Supervision to Exploration: What Does Protein Language Model Learn During Reinforcement Learning? [76.288870982181]
  Protein language models (PLMs) have advanced computational protein science through large-scale pretraining and scalable architectures.<n> reinforcement learning (RL) has broadened exploration and enabled precise multi-objective optimization in protein design.<n>We ask if RL improves sampling efficiency and, more importantly, if it reveals capabilities not captured by supervised learning.
  arXiv  Detail & Related papers  (2025-10-02T01:31:10Z)
• ESSA: Evolutionary Strategies for Scalable Alignment [8.418036456622158]
  We present ESSA, a gradient-free framework that aligns Large Language Models (LLMs) using only forward inference and black-box optimization.<n>ESSA improves the test accuracy of Qwen2.5-Math-7B by 12.6% on GSM8K and 14.8% on PRM800K, and raises the accuracy of LLaMA3.1-8B on IFEval by 22.5%.<n>In large-scale settings ESSA shows stronger scaling than gradient-based methods.
  arXiv  Detail & Related papers  (2025-07-06T16:23:07Z)
• Assessing how hyperparameters impact Large Language Models' sarcasm detection performance [0.0]
  Sarcasm detection is challenging for both humans and machines. This work explores how model characteristics impact sarcasm detection in OpenAI's GPT, and Meta's Llama-2 models.
  arXiv  Detail & Related papers  (2025-04-08T16:05:25Z)
• Sample, Don't Search: Rethinking Test-Time Alignment for Language Models [55.2480439325792]
  We introduce QAlign, a new test-time alignment approach. As we scale test-time compute, QAlign converges to sampling from the optimal aligned distribution for each individual prompt. By adopting recent advances in Markov chain Monte Carlo for text generation, our method enables better-aligned outputs without modifying the underlying model or even requiring logit access.
  arXiv  Detail & Related papers  (2025-04-04T00:41:40Z)
• HALO: Hadamard-Assisted Lower-Precision Optimization for LLMs [45.37278584462772]
  We present HALO, a novel quantization-aware training approach for Transformers. Our approach ensures that all large matrix multiplications during the forward and backward passes are executed in lower precision. Applying to LLAMA-family models, HALO achieves near-full-precision-equivalent results during fine-tuning on various tasks.
  arXiv  Detail & Related papers  (2025-01-05T18:41:54Z)
• SWAN: SGD with Normalization and Whitening Enables Stateless LLM Training [16.037614012166063]
  Gradient Descent (SGD) is a stateless, scalability as it does not track state variables during training. In this work, we show that pre-processing SGD in a stateless manner can achieve the same performance as the Adam for training LLM. We show that normalization stabilizes gradient, and counteracts the local curvature of the loss landscape. This results in SWAN (SGD with Whitening And Normalization), aapprox that eliminates the need to store any states.
  arXiv  Detail & Related papers  (2024-12-17T18:13:18Z)
• Value Augmented Sampling for Language Model Alignment and Personalization [39.070662999014836]
  We present a new framework for reward optimization, Value Augmented Sampling (VAS) VAS solves for the optimal reward-maximizing policy without co-training the policy and the value function. Our algorithm unlocks the new capability of composing several rewards and controlling the extent of each one during deployment time.
  arXiv  Detail & Related papers  (2024-05-10T17:59:04Z)
• Iterative Reasoning Preference Optimization [84.15992372132507]
  We develop an iterative approach to optimize the preference between generated Chain-of-Thought (CoT) candidates. We show reasoning improves across repeated iterations of this scheme. For example, we see a large improvement from 55.6% to 81.6% on GSM8K and an accuracy of 88.7% with majority voting out of 32 samples.
  arXiv  Detail & Related papers  (2024-04-30T17:28:05Z)
• Hybrid-Task Meta-Learning: A GNN Approach for Scalable and Transferable Bandwidth Allocation [50.96751567777229]
  We develop a deep learning-based bandwidth allocation policy that is scalable with the number of users and transferable to different communication scenarios.<n>To support scalability, the bandwidth allocation policy is represented by a graph neural network (GNN)<n>We develop a hybrid-task meta-learning (HML) algorithm that trains the initial parameters of the GNN with different communication scenarios.
  arXiv  Detail & Related papers  (2023-12-23T04:25:12Z)
• Exploring the impact of low-rank adaptation on the performance, efficiency, and regularization of RLHF [47.960563851948514]
  We investigate an efficient implementation of RLHF using low-rank adaptation (LoRA) Our implementation achieves better performance than the publicly-released AlpacaFarm checkpoint with full model fine-tuning. We release our code and pretrained checkpoints to facilitate future research on more efficient RLHF.
  arXiv  Detail & Related papers  (2023-09-16T17:31:36Z)
• An efficient hybrid classification approach for COVID-19 based on Harris Hawks Optimization and Salp Swarm Optimization [0.0]
  This study presents a hybrid binary version of the Harris Hawks Optimization algorithm (HHO) and Salp Swarm Optimization (SSA) for Covid-19 classification. The proposed algorithm (HHOSSA) achieved 96% accuracy with the SVM, 98% and 98% accuracy with two classifiers.
  arXiv  Detail & Related papers  (2022-12-25T19:52:18Z)
• Scaling & Shifting Your Features: A New Baseline for Efficient Model Tuning [126.84770886628833]
  Existing finetuning methods either tune all parameters of the pretrained model (full finetuning) or only tune the last linear layer (linear probing) We propose a new parameter-efficient finetuning method termed as SSF, representing that researchers only need to Scale and Shift the deep Features extracted by a pre-trained model to catch up with the performance full finetuning.
  arXiv  Detail & Related papers  (2022-10-17T08:14:49Z)
• GDI: Rethinking What Makes Reinforcement Learning Different From Supervised Learning [8.755783981297396]
  We extend the basic paradigm of RL called the Generalized Policy Iteration (GPI) into a more generalized version, which is called the Generalized Data Distribution Iteration (GDI) Our algorithm has achieved 9620.98% mean human normalized score (HNS), 1146.39% median HNS and 22 human world record breakthroughs (HWRB) using only 200 training frames.
  arXiv  Detail & Related papers  (2021-06-11T08:31:12Z)
• Improving Calibration for Long-Tailed Recognition [68.32848696795519]
  We propose two methods to improve calibration and performance in such scenarios. For dataset bias due to different samplers, we propose shifted batch normalization. Our proposed methods set new records on multiple popular long-tailed recognition benchmark datasets.
  arXiv  Detail & Related papers  (2021-04-01T13:55:21Z)
• MALI: A memory efficient and reverse accurate integrator for Neural ODEs [11.786863362728868]
  Memory-efficient ALF integrator (MALI) for Neural ordinary differential equations (Neural ODEs) MALI is first to enable feasible training of a Neural ODE on ImageNet and outperform a well-tuned ResNet. For time series modeling, MALI significantly outperforms the adjoint method. For continuous generative models, MALI achieves new state-of-the-art performance.
  arXiv  Detail & Related papers  (2021-02-09T06:33:47Z)
• A Self-Tuning Actor-Critic Algorithm [57.46821456365635]
  Self-Tuning Actor-Critic (STAC) is an algorithm for reinforcement learning. STAC is simple to use, sample efficient and does not require a significant increase in compute. Studies show that STAC improved the median human normalized score in 200M steps from 243% to 364%.
  arXiv  Detail & Related papers  (2020-02-28T18:55:38Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.